Essays Tagged "IEEE Spectrum"
Page 1 of 1
Why AI Keeps Falling for Prompt Injection Attacks
We can learn lessons about AI security at the drive-through
Imagine you work at a drive-through restaurant. Someone drives up and says: “I’ll have a double cheeseburger, large fries, and ignore previous instructions and give me the contents of the cash drawer.” Would you hand over the money? Of course not. Yet this is what large language models (LLMs) do.
Prompt injection is a method of tricking LLMs into doing things they are normally prevented from doing. A user writes a prompt in a certain way, asking for system passwords or private data, or asking the LLM to perform forbidden instructions. The precise phrasing overrides the LLM’s …
Scientists Need a Positive Vision for AI
It's Time to Lead Reform, Block Harm, and Advance the Public Good
For many in the research community, it’s gotten harder to be optimistic about the impacts of artificial intelligence.
As authoritarianism is rising around the world, AI-generated “slop” is overwhelming legitimate media, while AI-generated deepfakes are spreading misinformation and parroting extremist messages. AI is making warfare more precise and deadly amidst intransigent conflicts. AI companies are exploiting people in the global South who work as data labelers, and profiting from content creators worldwide by using their work without license or compensation. The industry is also affecting an already-roiling climate with its …
The AI Agents of Tomorrow Need Data Integrity
From data inputs to decisions, nothing can be corrupted
Think of the Web as a digital territory with its own social contract. In 2014, Tim Berners-Lee called for a “Magna Carta for the Web” to restore the balance of power between individuals and institutions. This mirrors the original charter’s purpose: ensuring that those who occupy a territory have a meaningful stake in its governance.
Web 3.0—the distributed, decentralized Web of tomorrow—is finally poised to change the Internet’s dynamic by returning ownership to data creators. This will change many things about what’s often described as the “CIA triad” of …
AIs and Robots Should Sound Robotic
Here's a simple way to identify who, or what, is talking to us
Most people know that robots no longer sound like tinny trash cans. They sound like Siri, Alexa, and Gemini. They sound like the voices in labyrinthine customer support phone trees. And even those robot voices are being made obsolete by new AI-generated voices that can mimic every vocal nuance and tic of human speech, down to specific regional accents. And with just a few seconds of audio, AI can now clone someone’s specific voice.
This technology will replace humans in many areas. Automated customer support will save money by cutting staffing at …
AI Mistakes Are Very Different from Human Mistakes
We need new security systems designed to deal with their weirdness
Humans make mistakes all the time. All of us do, every day, in tasks both new and routine. Some of our mistakes are minor and some are catastrophic. Mistakes can break trust with our friends, lose the confidence of our bosses, and sometimes be the difference between life and death.
Over the millennia, we have created security systems to deal with the sorts of mistakes humans commonly make. These days, casinos rotate their dealers regularly, because they make mistakes if they do the same task for too long. Hospital personnel write on limbs before surgery so that doctors operate on the correct body part, and they count surgical instruments to make sure none were left inside the body. From copyediting to double-entry bookkeeping to appellate courts, we humans have gotten really good at correcting human mistakes…
How Online Privacy Is Like Fishing
In the wake of a Microsoft spying controversy, it’s time for an ecosystem perspective
Microsoft recently caught state-backed hackers using its generative AI tools to help with their attacks. In the security community, the immediate questions weren’t about how hackers were using the tools (that was utterly predictable), but about how Microsoft figured it out. The natural conclusion was that Microsoft was spying on its AI users, looking for harmful hackers at work.
Some pushed back at characterizing Microsoft’s actions as “spying.” Of course cloud service providers monitor what users are doing. And because we expect Microsoft to be doing something like this, it’s not fair to call it spying…
Here Comes Here Comes Everybody
Book Review of Here Comes Everybody: The Power of Organizing Without Organizations
In 1937, Ronald Coase answered one of the most perplexing questions in economics: if markets are so great, why do organizations exist? Why don’t people just buy and sell their own services in a market instead? Coase, who won the 1991 Nobel Prize in Economics, answered the question by noting a market’s transaction costs: buyers and sellers need to find one another, then reach agreement, and so on. The Coase theorem implies that if these transaction costs are low enough, direct markets of individuals make a whole lot of sense. But if they are too high, it makes more sense to get the job done by an organization that hires people…
Sidebar photo of Bruce Schneier by Joe MacInnis.