October 15, 2023
by Bruce Schneier
Fellow and Lecturer, Harvard Kennedy School
A free monthly newsletter providing summaries, analyses, insights, and commentaries on security: computer and otherwise.
For back issues, or to subscribe, visit Crypto-Gram’s web page.
These same essays and news items appear in the Schneier on Security blog, along with a lively and intelligent comment section. An RSS feed is available.
- On Technologies for Automatic Facial Recognition
- LLM Summary of My Book Beyond Fear
- Using Hacked LastPass Keys to Steal Cryptocurrency
- Detecting AI-Generated Text
- On the Cybersecurity Jobs Shortage
- New Revelations from the Snowden Documents
- Signal Will Leave the UK Rather Than Add a Backdoor
- Critical Vulnerability in libwebp Library
- NSA AI Security Center
- Hacking Gas Pumps via Bluetooth
- Malicious Ads in Bing Chat
- Political Disinformation and AI
- Deepfake Election Interference in Slovakia
- AI Risks
- Model Extraction Attack on Neural Networks
- Cisco Can’t Stop Using Hard-Coded Passwords
- Bounty to Recover NIST’s Elliptic Curve Seeds
- Hacking the High School Grading System
With technology like that on Mr. Leyvand’s head, Facebook could prevent users from ever forgetting a colleague’s name, give a reminder at a cocktail party that an acquaintance had kids to ask about or help find someone at a crowded conference. However, six years later, the company now known as Meta has not released a version of that product and Mr. Leyvand has departed for Apple to work on its Vision Pro augmented reality glasses.
The technology is here. Maybe the implementation is still dorky, but that will change. The social implications will be enormous.
[2023.09.15] Claude (Anthropic’s LLM) was given this prompt: Please summarize the themes and arguments of Bruce Schneier’s book Beyond Fear. I’m particularly interested in a taxonomy of his ethical arguments—please expand on that. Then lay out the most salient criticisms of the book.
Here’s a brief summary of the key themes and arguments made in security expert Bruce Schneier’s book Beyond Fear: Thinking Sensibly About Security in an Uncertain World:
- Effective security requires realistic risk assessment, not fear-driven responses. We need to rationally determine actual threats versus perceived ones.
- Security trade-offs need to be carefully balanced against costs to other values like privacy, freedom, and social/economic impacts.
- Human psychology and biases lead to exaggerated fears that politicians/marketers can exploit, resulting in wasteful and theatrical “security theater.”
- Security is a process that requires ongoing flexibility, not total prevention. We can’t anticipate every threat but can build resilience.
- Analyze risks empirically using evidence, statistics, and probability rather than intuition. Avoid underestimating everyday risks while overestimating novel or sensational ones.
- Reject the temptation to implement oppressive security restrictions after tragic but unlikely events. Focus only on proportional responses.
- Where possible, favor openness and transparency over aggressive data collection or restrictions which erode civil liberties.
- Seek security policies and technologies that enhance society broadly rather than benefit special interests.
Schneier argues for rational, ethical approaches to security aimed at genuine protection while avoiding violations of human rights in the name of safety.
Here are some of the key ethical arguments Bruce Schneier makes in Beyond Fear regarding security policy and practices:
- Utilitarian Ethics—Security measures should aim to provide the greatest societal benefit and well-being for the most people, not just special interests.
- Individual Autonomy—Restrictions should be minimized to avoid excessive infringements on civil liberties and individual freedoms. Surveillance creep risks violating autonomy.
- Privacy Rights—Pervasive monitoring and data collection erode privacy rights and dignity. Citizens are entitled to some degree of opacity.
- Proportional Responses—Reactive policies should weigh costs versus statistically likely benefits. Draconian rules beyond proportionality are unethical.
- Justice and Fairness—Security should not create racial, religious or other profiling biases that punish groups rather than conduct.
- Accountability and Transparency—Ethical security requires checks against excessive power and oversight for responsibility. Secrecy enables abuses.
- Honest Representation—Officials and pundits have an ethical duty not to stoke disproportionate public fears. Security theater manufactures consent.
- Integrity and Character—Leaders should have the wisdom and courage to make difficult trade-offs rather than exploit fears for authority and control.
Overall Schneier argues security policies grounded in ethics rather than fear promote human well-being while recognizing inherent trade-offs. Prudence, transparency, and proportionality are essential.
Here are some of the most salient criticisms made against the arguments put forth in Bruce Schneier’s book Beyond Fear:
- Downplays real threats—Some argue Schneier dangerously downplays serious risks like terrorism and cybercrime by calling fears overblown.
- Too theoretical—His risk analysis approach may rely too much on statistics versus real-world uncertainties that defy probabilistic reasoning.
- No easy answers—While citing misguided policies, critics say Schneier provides few actionable solutions or concrete policy guidance.
- Conflicting values—His balancing of security, privacy and liberty involves inherent trade-offs and tough choices he gives little direction on.
- Politically naive—Suggesting special interests drive policy may under-appreciate legitimate national security concerns of elected officials.
- Hindsight bias—Assessing past overreactions easier than predicting future threats that justify caution today.
- No accounting for psychology—Factoring human irrationality into policy is essential, not dismissed as “security theater.”
- Technical focus—Focuses narrowly on certain technologies while ignoring broader organizational and sociological dimensions.
In summary, critics argue Schneier’s risk analysis orientation is too clinical, abstract, and devoid of political and human realities to transform concrete policy in the ways he intends. His framework may therefore lack sufficient nuance or guidance.
It’s interesting. The summary is pretty accurate, and so are the criticisms. The book was a product of my thinking twenty years ago, and my own thinking has evolved to address those criticisms.
Of course, this only works with older books that the LLM has ingested, and probably works better with books that have been written about.
Well, they’re now using that data break into crypto wallets and drain them: $35 million and counting, all going into a single wallet.
That’s a really profitable hack. (It’s also bad opsec. The hackers need to move and launder all that money quickly.)
Look, I know that online password databases are more convenient. But they’re also risky. This is why my Password Safe is local only. (I know this sounds like a commercial, but Password Safe is not a commercial product.)
Do AI detectors work?
- In short, no. While some (including OpenAI) have released tools that purport to detect AI-generated content, none of these have proven to reliably distinguish between AI-generated and human-generated content.
- Additionally, ChatGPT has no “knowledge” of what content could be AI-generated. It will sometimes make up responses to questions like “did you write this [essay]?” or “could this have been written by AI?” These responses are random and have no basis in fact.
- To elaborate on our research into the shortcomings of detectors, one of our key findings was that these tools sometimes suggest that human-written content was generated by AI.
- When we at OpenAI tried to train an AI-generated content detector, we found that it labeled human-written text like Shakespeare and the Declaration of Independence as AI-generated.
- There were also indications that it could disproportionately impact students who had learned or were learning English as a second language and students whose writing was particularly formulaic or concise.
- Even if these tools could accurately identify AI-generated content (which they cannot yet), students can make small edits to evade detection.
There is some good research in watermarking LLM-generated text, but the watermarks are not generally robust.
I don’t think the detectors are going to win this arms race.
Global cybersecurity job vacancies grew by 350 percent, from one million openings in 2013 to 3.5 million in 2021, according to Cybersecurity Ventures. The number of unfilled jobs leveled off in 2022, and remains at 3.5 million in 2023, with more than 750,000 of those positions in the U.S. Industry efforts to source new talent and tackle burnout continues, but we predict that the disparity between demand and supply will remain through at least 2025.
The numbers never made sense to me, and Ben Rothke has dug in and explained the reality:
…there is not a shortage of security generalists, middle managers, and people who claim to be competent CISOs. Nor is there a shortage of thought leaders, advisors, or self-proclaimed cyber subject matter experts. What there is a shortage of are computer scientists, developers, engineers, and information security professionals who can code, understand technical security architecture, product security and application security specialists, analysts with threat hunting and incident response skills. And this is nothing that can be fixed by a newbie taking a six-month information security boot camp.
Most entry-level roles tend to be quite specific, focused on one part of the profession, and are not generalist roles. For example, hiring managers will want a network security engineer with knowledge of networks or an identity management analyst with experience in identity systems. They are not looking for someone interested in security.
In fact, security roles are often not considered entry-level at all. Hiring managers assume you have some other background, usually technical before you are ready for an entry-level security job. Without those specific skills, it is difficult for a candidate to break into the profession. Job seekers learn that entry-level often means at least two to three years of work experience in a related field.
That makes a lot more sense, and matches what I experience.
Kind of amazing that that all happened ten years ago. At this point, those documents are more historical than anything else.
And it’s unclear who has those archives anymore. According to Appelbaum, The Intercept destroyed their copy.
I recently published an essay about my experiences ten years ago.
Onstage at TechCrunch Disrupt 2023, Meredith Whittaker, the president of the Signal Foundation, which maintains the nonprofit Signal messaging app, reaffirmed that Signal would leave the U.K. if the country’s recently passed Online Safety Bill forced Signal to build “backdoors” into its end-to-end encryption.
“We would leave the U.K. or any jurisdiction if it came down to the choice between backdooring our encryption and betraying the people who count on us for privacy, or leaving,” Whittaker said. “And that’s never not true.”
[2023.09.27] Both Apple and Google have recently reported critical vulnerabilities in their systems—iOS and Chrome, respectively—that are ultimately the result of the same vulnerability in the libwebp library:
On Thursday, researchers from security firm Rezillion published evidence that they said made it “highly likely” both indeed stemmed from the same bug, specifically in libwebp, the code library that apps, operating systems, and other code libraries incorporate to process WebP images.
Rather than Apple, Google, and Citizen Lab coordinating and accurately reporting the common origin of the vulnerability, they chose to use a separate CVE designation, the researchers said. The researchers concluded that “millions of different applications” would remain vulnerable until they, too, incorporated the libwebp fix. That, in turn, they said, was preventing automated systems that developers use to track known vulnerabilities in their offerings from detecting a critical vulnerability that’s under active exploitation.
EDITED TO ADD (10/12): Google quietly corrected their disclosure.
The AI security center’s establishment follows an NSA study that identified securing AI models from theft and sabotage as a major national security challenge, especially as generative AI technologies emerge with immense transformative potential for both good and evil.
Nakasone said it would become “NSA’s focal point for leveraging foreign intelligence insights, contributing to the development of best practices guidelines, principles, evaluation, methodology and risk frameworks” for both AI security and the goal of promoting the secure development and adoption of AI within “our national security systems and our defense industrial base.”
He said it would work closely with U.S. industry, national labs, academia and the Department of Defense as well as international partners.
[2023.10.03] Turns out pumps at gas stations are controlled via Bluetooth, and that the connections are insecure. No details in the article, but it seems that it’s easy to take control of the pump and have it dispense gas without requiring payment.
It’s a complicated crime to monetize, though. You need to sell access to the gas pump to others.
[2023.10.05] Elections around the world are facing an evolving threat from foreign actors, one that involves artificial intelligence.
Countries trying to influence each other’s elections entered a new era in 2016, when the Russians launched a series of social media disinformation campaigns targeting the US presidential election. Over the next seven years, a number of countries—most prominently China and Iran—used social media to influence foreign elections, both in the US and elsewhere in the world. There’s no reason to expect 2023 and 2024 to be any different.
But there is a new element: generative AI and large language models. These have the ability to quickly and easily produce endless reams of text on any topic in any tone from any perspective. As a security expert, I believe it’s a tool uniquely suited to Internet-era propaganda.
This is all very new. ChatGPT was introduced in November 2022. The more powerful GPT-4 was released in March 2023. Other language and image production AIs are around the same age. It’s not clear how these technologies will change disinformation, how effective they will be or what effects they will have. But we are about to find out.
Election season will soon be in full swing in much of the democratic world. Seventy-one percent of people living in democracies will vote in a national election between now and the end of next year. Among them: Argentina and Poland in October, Taiwan in January, Indonesia in February, India in April, the European Union and Mexico in June, and the US in November. Nine African democracies, including South Africa, will have elections in 2024. Australia and the UK don’t have fixed dates, but elections are likely to occur in 2024.
Many of those elections matter a lot to the countries that have run social media influence operations in the past. China cares a great deal about Taiwan, Indonesia, India, and many African countries. Russia cares about the UK, Poland, Germany, and the EU in general. Everyone cares about the United States.
And that’s only considering the largest players. Every US national election from 2016 has brought with it an additional country attempting to influence the outcome. First it was just Russia, then Russia and China, and most recently those two plus Iran. As the financial cost of foreign influence decreases, more countries can get in on the action. Tools like ChatGPT significantly reduce the price of producing and distributing propaganda, bringing that capability within the budget of many more countries.
A couple of months ago, I attended a conference with representatives from all of the cybersecurity agencies in the US. They talked about their expectations regarding election interference in 2024. They expected the usual players—Russia, China, and Iran—and a significant new one: “domestic actors.” That is a direct result of this reduced cost.
Of course, there’s a lot more to running a disinformation campaign than generating content. The hard part is distribution. A propagandist needs a series of fake accounts on which to post, and others to boost it into the mainstream where it can go viral. Companies like Meta have gotten much better at identifying these accounts and taking them down. Just last month, Meta announced that it had removed 7,704 Facebook accounts, 954 Facebook pages, 15 Facebook groups, and 15 Instagram accounts associated with a Chinese influence campaign, and identified hundreds more accounts on TikTok, X (formerly Twitter), LiveJournal, and Blogspot. But that was a campaign that began four years ago, producing pre-AI disinformation.
Disinformation is an arms race. Both the attackers and defenders have improved, but also the world of social media is different. Four years ago, Twitter was a direct line to the media, and propaganda on that platform was a way to tilt the political narrative. A Columbia Journalism Review study found that most major news outlets used Russian tweets as sources for partisan opinion. That Twitter, with virtually every news editor reading it and everyone who was anyone posting there, is no more.
Many propaganda outlets moved from Facebook to messaging platforms such as Telegram and WhatsApp, which makes them harder to identify and remove. TikTok is a newer platform that is controlled by China and more suitable for short, provocative videos—ones that AI makes much easier to produce. And the current crop of generative AIs are being connected to tools that will make content distribution easier as well.
Generative AI tools also allow for new techniques of production and distribution, such as low-level propaganda at scale. Imagine a new AI-powered personal account on social media. For the most part, it behaves normally. It posts about its fake everyday life, joins interest groups and comments on others’ posts, and generally behaves like a normal user. And once in a while, not very often, it says—or amplifies—something political. These persona bots, as computer scientist Latanya Sweeney calls them, have negligible influence on their own. But replicated by the thousands or millions, they would have a lot more.
That’s just one scenario. The military officers in Russia, China, and elsewhere in charge of election interference are likely to have their best people thinking of others. And their tactics are likely to be much more sophisticated than they were in 2016.
Countries like Russia and China have a history of testing both cyberattacks and information operations on smaller countries before rolling them out at scale. When that happens, it’s important to be able to fingerprint these tactics. Countering new disinformation campaigns requires being able to recognize them, and recognizing them requires looking for and cataloging them now.
In the computer security world, researchers recognize that sharing methods of attack and their effectiveness is the only way to build strong defensive systems. The same kind of thinking also applies to these information campaigns: The more that researchers study what techniques are being employed in distant countries, the better they can defend their own countries.
Disinformation campaigns in the AI era are likely to be much more sophisticated than they were in 2016. I believe the US needs to have efforts in place to fingerprint and identify AI-produced propaganda in Taiwan, where a presidential candidate claims a deepfake audio recording has defamed him, and other places. Otherwise, we’re not going to see them when they arrive here. Unfortunately, researchers are instead being targeted and harassed.
Maybe this will all turn out okay. There have been some important democratic elections in the generative AI era with no significant disinformation issues: primaries in Argentina, first-round elections in Ecuador, and national elections in Thailand, Turkey, Spain, and Greece. But the sooner we know what to expect, the better we can deal with what comes.
This essay previously appeared in The Conversation.
Šimečka and Denník N immediately denounced the audio as fake. The fact-checking department of news agency AFP said the audio showed signs of being manipulated using AI. But the recording was posted during a 48-hour moratorium ahead of the polls opening, during which media outlets and politicians are supposed to stay silent. That meant, under Slovakia’s election rules, the post was difficult to widely debunk. And, because the post was audio, it exploited a loophole in Meta’s manipulated-media policy, which dictates only faked videos—where a person has been edited to say words they never said—go against its rules.
I just wrote about this. Countries like Russia and China tend to test their attacks out on smaller countries before unleashing them on larger ones. Consider this a preview to their actions in the US next year.
[2023.10.09] There is no shortage of researchers and industry titans willing to warn us about the potential destructive power of artificial intelligence. Reading the headlines, one would hope that the rapid gains in AI technology have also brought forth a unifying realization of the risks—and the steps we need to take to mitigate them.
The reality, unfortunately, is quite different. Beneath almost all of the testimony, the manifestoes, the blog posts, and the public declarations issued about AI are battles among deeply divided factions. Some are concerned about far-future risks that sound like science fiction. Some are genuinely alarmed by the practical problems that chatbots and deepfake video generators are creating right now. Some are motivated by potential business revenue, others by national security concerns.
The result is a cacophony of coded language, contradictory views, and provocative policy demands that are undermining our ability to grapple with a technology destined to drive the future of politics, our economy, and even our daily lives.
These factions are in dialogue not only with the public but also with one another. Sometimes, they trade letters, opinion essays, or social threads outlining their positions and attacking others’ in public view. More often, they tout their viewpoints without acknowledging alternatives, leaving the impression that their enlightened perspective is the inevitable lens through which to view AI But if lawmakers and the public fail to recognize the subtext of their arguments, they risk missing the real consequences of our possible regulatory and cultural paths forward.
To understand the fight and the impact it may have on our shared future, look past the immediate claims and actions of the players to the greater implications of their points of view. When you do, you’ll realize this isn’t really a debate only about AI. It’s also a contest about control and power, about how resources should be distributed and who should be held accountable.
Beneath this roiling discord is a true fight over the future of society. Should we focus on avoiding the dystopia of mass unemployment, a world where China is the dominant superpower or a society where the worst prejudices of humanity are embodied in opaque algorithms that control our lives? Should we listen to wealthy futurists who discount the importance of climate change because they’re already thinking ahead to colonies on Mars? It is critical that we begin to recognize the ideologies driving what we are being told. Resolving the fracas requires us to see through the specter of AI to stay true to the humanity of our values.
One way to decode the motives behind the various declarations is through their language. Because language itself is part of their battleground, the different AI camps tend not to use the same words to describe their positions. One faction describes the dangers posed by AI through the framework of safety, another through ethics or integrity, yet another through security, and others through economics. By decoding who is speaking and how AI is being described, we can explore where these groups differ and what drives their views.
The loudest perspective is a frightening, dystopian vision in which AI poses an existential risk to humankind, capable of wiping out all life on Earth. AI, in this vision, emerges as a godlike, superintelligent, ungovernable entity capable of controlling everything. AI could destroy humanity or pose a risk on par with nukes. If we’re not careful, it could kill everyone or enslave humanity. It’s likened to monsters like the Lovecraftian shoggoths, artificial servants that rebelled against their creators, or paper clip maximizers that consume all of Earth’s resources in a single-minded pursuit of their programmed goal. It sounds like science fiction, but these people are serious, and they mean the words they use.
These are the AI safety people, and their ranks include the “Godfathers of AI,” Geoff Hinton and Yoshua Bengio. For many years, these leading lights battled critics who doubted that a computer could ever mimic capabilities of the human mind. Having steamrollered the public conversation by creating large language models like ChatGPT and other AI tools capable of increasingly impressive feats, they appear deeply invested in the idea that there is no limit to what their creations will be able to accomplish.
This doomsaying is boosted by a class of tech elite that has enormous power to shape the conversation. And some in this group are animated by the radical effective altruism movement and the associated cause of long-term-ism, which tend to focus on the most extreme catastrophic risks and emphasize the far-future consequences of our actions. These philosophies are hot among the cryptocurrency crowd, like the disgraced former billionaire Sam Bankman-Fried, who at one time possessed sudden wealth in search of a cause.
Reasonable sounding on their face, these ideas can become dangerous if stretched to their logical extremes. A dogmatic long-termer would willingly sacrifice the well-being of people today to stave off a prophesied extinction event like AI enslavement.
Many doomsayers say they are acting rationally, but their hype about hypothetical existential risks amounts to making a misguided bet with our future. In the name of long-term-ism, Elon Musk reportedly believes that our society needs to encourage reproduction among those with the greatest culture and intelligence (namely, his ultrarich buddies). And he wants to go further, such as limiting the right to vote to parents and even populating Mars. It’s widely believed that Jaan Tallinn, the wealthy long-termer who co-founded the most prominent centers for the study of AI safety, has made dismissive noises about climate change because he thinks that it pales in comparison with far-future unknown unknowns like risks from AI. The technology historian David C. Brock calls these fears “wishful worries”—that is, “problems that it would be nice to have, in contrast to the actual agonies of the present.”
More practically, many of the researchers in this group are proceeding full steam ahead in developing AI, demonstrating how unrealistic it is to simply hit pause on technological development. But the roboticist Rodney Brooks has pointed out that we will see the existential risks coming—the dangers will not be sudden and we will have time to change course. While we shouldn’t dismiss the Hollywood nightmare scenarios out of hand, we must balance them with the potential benefits of AI and, most important, not allow them to strategically distract from more immediate concerns. Let’s not let apocalyptic prognostications overwhelm us and smother the momentum we need to develop critical guardrails.
While the doomsayer faction focuses on the far-off future, its most prominent opponents are focused on the here and now. We agree with this group that there’s plenty already happening to cause concern: Racist policing and legal systems that disproportionately arrest and punish people of color. Sexist labor systems that rate feminine-coded résumés lower. Superpower nations automating military interventions as tools of imperialism and, someday, killer robots.
The alternative to the end-of-the-world, existential risk narrative is a distressingly familiar vision of dystopia: a society in which humanity’s worst instincts are encoded into and enforced by machines. The doomsayers think AI enslavement looks like the Matrix; the reformers point to modern-day contractors doing traumatic work at low pay for OpenAI in Kenya.
Propagators of these AI ethics concerns—like Meredith Broussard, Safiya Umoja Noble, Rumman Chowdhury, and Cathy O’Neil—have been raising the alarm on inequities coded into AI for years. Although we don’t have a census, it’s noticeable that many leaders in this cohort are people of color, women, and people who identify as LGBTQ. They are often motivated by insight into what it feels like to be on the wrong end of algorithmic oppression and by a connection to the communities most vulnerable to the misuse of new technology. Many in this group take an explicitly social perspective: When Joy Buolamwini founded an organization to fight for equitable AI, she called it the Algorithmic Justice League. Ruha Benjamin called her organization the Ida B. Wells Just Data Lab.
Others frame efforts to reform AI in terms of integrity, calling for Big Tech to adhere to an oath to consider the benefit of the broader public alongside—or even above—their self-interest. They point to social media companies’ failure to control hate speech or how online misinformation can undermine democratic elections. Adding urgency for this group is that the very companies driving the AI revolution have, at times, been eliminating safeguards. A signal moment came when Timnit Gebru, a co-leader of Google’s AI ethics team, was dismissed for pointing out the risks of developing ever-larger AI language models.
While doomsayers and reformers share the concern that AI must align with human interests, reformers tend to push back hard against the doomsayers’ focus on the distant future. They want to wrestle the attention of regulators and advocates back toward present-day harms that are exacerbated by AI misinformation, surveillance, and inequity. Integrity experts call for the development of responsible AI, for civic education to ensure AI literacy and for keeping humans front and center in AI systems.
This group’s concerns are well documented and urgent—and far older than modern AI technologies. Surely, we are a civilization big enough to tackle more than one problem at a time; even those worried that AI might kill us in the future should still demand that it not profile and exploit us in the present.
Other groups of prognosticators cast the rise of AI through the language of competitiveness and national security. One version has a post-9/11 ring to it—a world where terrorists, criminals, and psychopaths have unfettered access to technologies of mass destruction. Another version is a Cold War narrative of the United States losing an AI arms race with China and its surveillance-rich society.
Some arguing from this perspective are acting on genuine national security concerns, and others have a simple motivation: money. These perspectives serve the interests of American tech tycoons as well as the government agencies and defense contractors they are intertwined with.
OpenAI’s Sam Altman and Meta’s Mark Zuckerberg, both of whom lead dominant AI companies, are pushing for AI regulations that they say will protect us from criminals and terrorists. Such regulations would be expensive to comply with and are likely to preserve the market position of leading AI companies while restricting competition from start-ups. In the lobbying battles over Europe’s trailblazing AI regulatory framework, US megacompanies pleaded to exempt their general-purpose AI from the tightest regulations, and whether and how to apply high-risk compliance expectations on noncorporate open-source models emerged as a key point of debate. All the while, some of the moguls investing in upstart companies are fighting the regulatory tide. The Inflection AI co-founder Reid Hoffman argued, “The answer to our challenges is not to slow down technology but to accelerate it.”
Any technology critical to national defense usually has an easier time avoiding oversight, regulation, and limitations on profit. Any readiness gap in our military demands urgent budget increases and funds distributed to the military branches and their contractors, because we may soon be called upon to fight. Tech moguls like Google’s former chief executive Eric Schmidt, who has the ear of many lawmakers, signal to American policymakers about the Chinese threat even as they invest in US national security concerns.
The warriors’ narrative seems to misrepresent that science and engineering are different from what they were during the mid-twentieth century. AI research is fundamentally international; no one country will win a monopoly. And while national security is important to consider, we must also be mindful of self-interest of those positioned to benefit financially.
As the science-fiction author Ted Chiang has said, fears about the existential risks of AI are really fears about the threat of uncontrolled capitalism, and dystopias like the paper clip maximizer are just caricatures of every start-up’s business plan. Cosma Shalizi and Henry Farrell further argue that “we’ve lived among shoggoths for centuries, tending to them as though they were our masters” as monopolistic platforms devour and exploit the totality of humanity’s labor and ingenuity for their own interests. This dread applies as much to our future with AI as it does to our past and present with corporations.
Regulatory solutions do not need to reinvent the wheel. Instead, we need to double down on the rules that we know limit corporate power. We need to get more serious about establishing good and effective governance on all the issues we lost track of while we were becoming obsessed with AI, China, and the fights picked among robber barons.
By analogy to the healthcare sector, we need an AI public option to truly keep AI companies in check. A publicly directed AI development project would serve to counterbalance for-profit corporate AI and help ensure an even playing field for access to the twenty-first century’s key technology while offering a platform for the ethical development and use of AI.
Also, we should embrace the humanity behind AI. We can hold founders and corporations accountable by mandating greater AI transparency in the development stage, in addition to applying legal standards for actions associated with AI. Remarkably, this is something that both the left and the right can agree on.
Ultimately, we need to make sure the network of laws and regulations that govern our collective behavior is knit more strongly, with fewer gaps and greater ability to hold the powerful accountable, particularly in those areas most sensitive to our democracy and environment. As those with power and privilege seem poised to harness AI to accumulate much more or pursue extreme ideologies, let’s think about how we can constrain their influence in the public square rather than cede our attention to their most bombastic nightmare visions for the future.
This essay was written with Nathan Sanders, and previously appeared in the New York Times.
Polynomial Time Cryptanalytic Extraction of Neural Network Models
Abstract: Billions of dollars and countless GPU hours are currently spent on training Deep Neural Networks (DNNs) for a variety of tasks. Thus, it is essential to determine the difficulty of extracting all the parameters of such neural networks when given access to their black-box implementations. Many versions of this problem have been studied over the last 30 years, and the best current attack on ReLU-based deep neural networks was presented at Crypto’20 by Carlini, Jagielski, and Mironov. It resembles a differential chosen plaintext attack on a cryptosystem, which has a secret key embedded in its black-box implementation and requires a polynomial number of queries but an exponential amount of time (as a function of the number of neurons).
In this paper, we improve this attack by developing several new techniques that enable us to extract with arbitrarily high precision all the real-valued parameters of a ReLU-based DNN using a polynomial number of queries and a polynomial amount of time. We demonstrate its practical efficiency by applying it to a full-sized neural network for classifying the CIFAR10 dataset, which has 3072 inputs, 8 hidden layers with 256 neurons each, and about 1.2 million neuronal parameters. An attack following the approach by Carlini et al. requires an exhaustive search over 2256 possibilities. Our attack replaces this with our new techniques, which require only 30 minutes on a 256-core computer.
This vulnerability is due to the presence of static user credentials for the root account that are typically reserved for use during development. An attacker could exploit this vulnerability by using the account to log in to an affected system. A successful exploit could allow the attacker to log in to the affected system and execute arbitrary commands as the root user.
The NIST elliptic curves that power much of modern cryptography were generated in the late ’90s by hashing seeds provided by the NSA. How were the seeds generated? Rumor has it that they are in turn hashes of English sentences, but the person who picked them, Dr. Jerry Solinas, passed away in early 2023 leaving behind a cryptographic mystery, some conspiracy theories, and an historical password cracking challenge.
So there’s a $12K prize to recover the hash seeds.
Some of the backstory here (it’s the funniest fucking backstory ever): it’s lately been circulating—though I think this may have been somewhat common knowledge among practitioners, though definitely not to me—that the “random” seeds for the NIST P-curves, generated in the 1990s by Jerry Solinas at NSA, were simply SHA1 hashes of some variation of the string “Give Jerry a raise”.
At the time, the “pass a string through SHA1” thing was meant to increase confidence in the curve seeds; the idea was that SHA1 would destroy any possible structure in the seed, so NSA couldn’t have selected a deliberately weak seed. Of course, NIST/NSA then set about destroying its reputation in the 2000’s, and this explanation wasn’t nearly enough to quell conspiracy theories.
But when Jerry Solinas went back to reconstruct the seeds, so NIST could demonstrate that the seeds really were benign, he found that he’d forgotten the string he used!
If you’re a true conspiracist, you’re certain nobody is going to find a string that generates any of these seeds. On the flip side, if anyone does find them, that’ll be a pretty devastating blow to the theory that the NIST P-curves were maliciously generated—even for people totally unfamiliar with basic curve math.
Note that this is not the constants used in the Dual_EC_PRNG random-number generator that the NSA backdoored. This is something different.
What’s not helping? The policies many school districts are adopting that make it nearly impossible for low-performing students to fail—they have a grading floor under them, they know it, and that allows them to game the system.
Several teachers whom I spoke with or who responded to my questionnaire mentioned policies stating that students cannot get lower than a 50 percent on any assignment, even if the work was never done, in some cases. A teacher from Chapel Hill, N.C., who filled in the questionnaire’s “name” field with “No, no, no,” said the 50 percent floor and “NO attendance enforcement” leads to a scenario where “we get students who skip over 100 days, have a 50 percent, complete a couple of assignments to tip over into 59.5 percent and then pass.”
It’s a basic math hack. If a student needs two-thirds of the points—over 65%—to pass, then they have to do two-thirds of the work. But if doing zero work results in a 50% grade, then they only have to do a little bit of work to get over the pass line.
I know this is a minor thing in the universe of problems with secondary education and grading, but I found the hack interesting. (And this is exactly the sort of thing I explore in my latest book: A Hacker’s Mind.
Since 1998, CRYPTO-GRAM has been a free monthly newsletter providing summaries, analyses, insights, and commentaries on security technology. To subscribe, or to read back issues, see Crypto-Gram’s web page.
You can also read these articles on my blog, Schneier on Security.
Please feel free to forward CRYPTO-GRAM, in whole or in part, to colleagues and friends who will find it valuable. Permission is also granted to reprint CRYPTO-GRAM, as long as it is reprinted in its entirety.
Bruce Schneier is an internationally renowned security technologist, called a security guru by the Economist. He is the author of over one dozen books—including his latest, A Hacker’s Mind—as well as hundreds of articles, essays, and academic papers. His newsletter and blog are read by over 250,000 people. Schneier is a fellow at the Berkman Klein Center for Internet & Society at Harvard University; a Lecturer in Public Policy at the Harvard Kennedy School; a board member of the Electronic Frontier Foundation, AccessNow, and the Tor Project; and an Advisory Board Member of the Electronic Privacy Information Center and VerifiedVoting.org. He is the Chief of Security Architecture at Inrupt, Inc.
Copyright © 2023 by Bruce Schneier.