Entries Tagged "hacking"

Page 1 of 78

How Dangerous Is Anthropic’s Mythos AI?

Last month, Anthropic made a remarkable announcement about its new model, Claude Mythos Preview: it was so good at finding security vulnerabilities in software that the company would not release it to the general public. Instead, it would only be available to a select group of companies to scan and fix their own software.

The announcement requires context—but it contained an essential truth.

While Anthropic’s model is really good at finding software vulnerabilities, so are other models. The UK’s AI Security Institute found that OpenAI’s GPT-5.5, already generally available, is comparable in capability. The company Aisle reproduced Anthropic’s published results with smaller, cheaper models.

At the same time, Anthropic’s refusal to publicly release its new model makes a virtue out of necessity. Mythos is very expensive to run, and the company doesn’t appear to have the resources for a general release. What better way to juice the company’s valuation than to hint at capabilities but not prove them, and then have others parrot their claims?

Nonetheless, the truth is scary. Modern generative AI systems—not just Anthropic’s, but OpenAI’s and other, open-source models—are getting really good at finding and exploiting vulnerabilities in software. And that has important ramifications for cybersecurity: on both the offense and the defense.

Attackers will use these capabilities to find, and automatically hack, vulnerabilities in systems of all kinds. They will be able to break into critical systems around the world, sometimes to plant ransomware and make money, sometimes to steal data for espionage purposes, and sometimes to control systems in times of hostility. This will make the world a much more dangerous, and more volatile, place.

But at the same time, defenders will use these same capabilities to find, and then patch, many of those same systems. For example, Mozilla used Mythos to find 271 vulnerabilities in Firefox. Those vulnerabilities have been fixed, and will never again be available to attackers. In the future, AIs automatically finding and fixing vulnerabilities in all software will be a normal part of the development process, which will result in much more secure software.

Of course, it’s not that simple. We should expect a deluge of both attackers using newly found vulnerabilities to break into systems, and at the same time much more frequent software updates for every app and device we use. But lots of systems aren’t patchable, and many systems that are don’t get patched, meaning that many vulnerabilities will stick around. And it does seem that finding and exploiting is easier than finding and fixing. All of this points to a more dangerous short-term future. Organizations will need to adapt their security to this new reality.

But it’s the long term that we need to focus on. Mythos isn’t unique, but it’s more capable than many models that have come before. And it’s less capable than models that will come after. AIs are much better at writing software than they were just six months ago. There’s every reason to believe that they will continue to get better, which means that they will get better at writing more secure software. The endgame gives AI-enhanced defenders advantages over AI-enhanced attackers.

Even more interesting are the broader implications. The same searching, pattern-matching and reasoning capabilities that make these models so good at analyzing software almost certainly apply to similar systems. The tax code isn’t computer code, but it’s a series of algorithms with inputs and outputs. It has vulnerabilities; we call them tax loopholes. It has exploits; we call them tax avoidance strategies. And it has black hat hackers: attorneys and accountants.

Just as these models are finding hundreds of vulnerabilities in complex software systems, we should expect them to be equally effective at finding many new and undiscovered tax loopholes. I am confident that the major investment banks are working on this right now, in secret. They’ve fed AI the tax code of the US, or the UK, or maybe every industrialized country, and tasked the system with looking for money-saving strategies. How many tax loopholes will those AIs find? Ten? One hundred? One thousand? The Double Dutch Irish Sandwich is a tax loophole that involves multiple different tax jurisdictions. Can AIs find loopholes even more complex? We have no idea.

Sure, the AIs will come up with a bunch of tricks that won’t work, but that’s where those attorneys and accountants come in—to verify, and then justify, the loopholes. And then to market them to their wealthy clients.

As goes the tax code, so goes any other complex system of rules and strategies. These models could be tasked with finding loopholes in environmental rules, or food and safety rules—anywhere there are complex regulatory systems and powerful people who want to evade those rules.

The results will be much worse than insecure computers. Tax loopholes result in less revenue collected by governments, and regulatory loopholes allow the powerful to skirt the rules, both of which have all sorts of social ramifications. And while software vendors can patch their systems in days, it generally takes years for a country to amend its tax code. And that process is political, with lobbyists pressuring legislators not to patch. Just look at the carried interest loophole, a US tax dodge that has been exploited for decades. Various administrations have tried to close the vulnerability, but legislators just can’t seem to resist lobbyists long enough to patch it.

AI technologies are poised to remake much of society. Just as the industrial revolution gave humans the ability to consume calories outside of their bodies at scale, the AI revolution will give humans the ability to perform cognitive tasks outside of their bodies at scale. Our systems aren’t designed for that; they’re designed for more human paces of cognition. We’re seeing it right now in the deluge of software vulnerabilities that these models are finding and exploiting. And we will soon see it in a deluge of vulnerabilities in all sorts of other systems of rules. Adapting to this new reality will be hard, but we don’t have any choice.

This essay originally appeared in The Guardian.

Posted on May 14, 2026 at 7:04 AM • View Comments

Rowhammer Attack Against NVIDIA Chips

A new rowhammer attack gives complete control of NVIDIA CPUs.

On Thursday, two research teams, working independently of each other, demonstrated attacks against two cards from Nvidia’s Ampere generation that take GPU rowhammering into new—­and potentially much more consequential—­territory: GDDR bitflips that give adversaries full control of CPU memory, resulting in full system compromise of the host machine. For the attack to work, IOMMU memory management must be disabled, as is the default in BIOS settings.

“Our work shows that Rowhammer, which is well-studied on CPUs, is a serious threat on GPUs as well,” said Andrew Kwong, co-author of one of the papers. “GDDRHammer: Greatly Disturbing DRAM Rows­Cross-Component Rowhammer Attacks from Modern GPUs.” “With our work, we… show how an attacker can induce bit flips on the GPU to gain arbitrary read/write access to all of the CPU’s memory, resulting in complete compromise of the machine.”

Update Friday, April 3: On Friday, researchers unveiled a third Rowhammer attack that also demonstrates Rowhammer attacks on the RTX A6000 that achieves privilege escalation to a root shell. Unlike the previous two, the researchers said, it works even when IOMMU is enabled.

The second paper is GeForge: Hammering GDDR Memory to Forge GPU Page Tables for Fun and Profit:

…does largely the same thing, except that instead of exploiting the last-level page table, as GDDRHammer does, it manipulates the last-level page directory. It was able to induce 1,171 bitflips against the RTX 3060 and 202 bitflips against the RTX 6000.

GeForge, too, uses novel hammering patterns and memory massaging to corrupt GPU page table mappings in GDDR6 memory to acquire read and write access to the GPU memory space. From there, it acquires the same privileges over host CPU memory. The GeForge proof-of-concept exploit against the RTX 3060 concludes by opening a root shell window that allows the attacker to issue commands that run unfettered privileges on the host machine. The researchers said that both GDDRHammer and GeForge could do the same thing against the RTC 6000.

Posted on May 6, 2026 at 6:36 AM • View Comments

Hacking Polymarket

Polymarket is a platform where people can bet on real-world events, political and otherwise. Leaving the ethical considerations of this aside (for one, it facilitates assassination), one of the issues with making this work is the verification of these real-world events. Polymarket gamblers have threatened a journalist because his story was being used to verify an event. And now, gamblers are taking hair dryers to weather sensors to rig weather bets.

There’s also insider trading: a lot of it.

Posted on May 4, 2026 at 5:46 AM • View Comments

Fast16 Malware

Researchers have reverse-engineered a piece of malware named Fast16. It’s almost certainly state-sponsored, probably US in origin, and was deployed against Iran years before Stuxnet:

“…the Fast16 malware was designed to carry out the most subtle form of sabotage ever seen in an in-the-wild malware tool: By automatically spreading across networks and then silently manipulating computation processes in certain software applications that perform high-precision mathematical calculations and simulate physical phenomena, Fast16 can alter the results of those programs to cause failures that range from faulty research results to catastrophic damage to real-world equipment.”

Another news article.

Lots of interesting details at the links.

Posted on April 30, 2026 at 6:22 AM • View Comments

How Hackers Are Thinking About AI

Interesting paper: “What hackers talk about when they talk about AI: Early-stage diffusion of a cybercrime innovation.”

Abstract: The rapid expansion of artificial intelligence (AI) is raising concerns about its potential to transform cybercrime. Beyond empowering novice offenders, AI stands to intensify the scale and sophistication of attacks by seasoned cybercriminals. This paper examines the evolving relationship between cybercriminals and AI using a unique dataset from a cyber threat intelligence platform. Analyzing more than 160 cybercrime forum conversations collected over seven months, our research reveals how cybercriminals understand AI and discuss how they can exploit its capabilities. Their exchanges reflect growing curiosity about AI’s criminal applications through legal tools and dedicated criminal tools, but also doubts and anxieties about AI’s effectiveness and its effects on their business models and operational security. The study documents attempts to misuse legitimate AI tools and develop bespoke models tailored for illicit purposes. Combining the diffusion of innovation framework with thematic analysis, the paper provides an in-depth view of emerging AI-enabled cybercrime and offers practical insights for law enforcement and policymakers.

Posted on April 14, 2026 at 6:49 AM • View Comments

Possible US Government iPhone Hacking Tool Leaked

Wired writes (alternate source):

Security researchers at Google on Tuesday released a report describing what they’re calling “Coruna,” a highly sophisticated iPhone hacking toolkit that includes five complete hacking techniques capable of bypassing all the defenses of an iPhone to silently install malware on a device when it visits a website containing the exploitation code. In total, Coruna takes advantage of 23 distinct vulnerabilities in iOS, a rare collection of hacking components that suggests it was created by a well-resourced, likely state-sponsored group of hackers.

[…]

Coruna’s code also appears to have been originally written by English-speaking coders, notes iVerify’s cofounder Rocky Cole. “It’s highly sophisticated, took millions of dollars to develop, and it bears the hallmarks of other modules that have been publicly attributed to the US government,” Cole tells WIRED. “This is the first example we’ve seen of very likely US government tools­based on what the code is telling us­spinning out of control and being used by both our adversaries and cybercriminal groups.”

TechCrunch reports that Coruna is definitely of US origin:

Two former employees of government contractor L3Harris told TechCrunch that Coruna was, at least in part, developed by the company’s hacking and surveillance tech division, Trenchant. The two former employees both had knowledge of the company’s iPhone hacking tools. Both spoke on condition of anonymity because they weren’t authorized to talk about their work for the company.

It’s always super interesting to see what malware looks like when it’s created through a professional software development process. And the TechCrunch article has some speculation as to how the US lost control of it. It seems that an employee of L3Harris’s surviellance tech division, Trenchant, sold it to the Russian government.

Posted on April 2, 2026 at 6:05 AM • View Comments

Is “Hackback” Official US Cybersecurity Strategy?

The 2026 US “Cyber Strategy for America” document is mostly the same thing we’ve seen out of the White House for over a decade, but with a more aggressive tone.

But one sentence stood out: “We will unleash the private sector by creating incentives to identify and disrupt adversary networks and scale our national capabilities.” This sounds like a call for hackback: giving private companies permission to conduct offensive cyber operations.

The Economist noticed (alternate link) this, too.

I think this is an incredibly dumb idea:

In warfare, the notion of counterattack is extremely powerful. Going after the enemy­—its positions, its supply lines, its factories, its infrastructure—­is an age-old military tactic. But in peacetime, we call it revenge, and consider it dangerous. Anyone accused of a crime deserves a fair trial. The accused has the right to defend himself, to face his accuser, to an attorney, and to be presumed innocent until proven guilty.

Both vigilante counterattacks, and preemptive attacks, fly in the face of these rights. They punish people before who haven’t been found guilty. It’s the same whether it’s an angry lynch mob stringing up a suspect, the MPAA disabling the computer of someone it believes made an illegal copy of a movie, or a corporate security officer launching a denial-of-service attack against someone he believes is targeting his company over the net.

In all of these cases, the attacker could be wrong. This has been true for lynch mobs, and on the internet it’s even harder to know who’s attacking you. Just because my computer looks like the source of an attack doesn’t mean that it is. And even if it is, it might be a zombie controlled by yet another computer; I might be a victim, too. The goal of a government’s legal system is justice; the goal of a vigilante is expediency.

We don’t issue letters of marque on the high seas anymore; we shouldn’t do it in cyberspace.

Posted on April 1, 2026 at 12:57 PM • View Comments

Microsoft Xbox One Hacked

It’s an impressive feat, over a decade after the box was released:

Since reset glitching wasn’t possible, Gaasedelen thought some voltage glitching could do the trick. So, instead of tinkering with the system rest pin(s) the hacker targeted the momentary collapse of the CPU voltage rail. This was quite a feat, as Gaasedelen couldn’t ‘see’ into the Xbox One, so had to develop new hardware introspection tools.

Eventually, the Bliss exploit was formulated, where two precise voltage glitches were made to land in succession. One skipped the loop where the ARM Cortex memory protection was setup. Then the Memcpy operation was targeted during the header read, allowing him to jump to the attacker-controlled data.

As a hardware attack against the boot ROM in silicon, Gaasedelen says the attack in unpatchable. Thus it is a complete compromise of the console allowing for loading unsigned code at every level, including the Hypervisor and OS. Moreover, Bliss allows access to the security processor so games, firmware, and so on can be decrypted.

Posted on March 23, 2026 at 7:01 AM • View Comments

Claude Used to Hack Mexican Government

An unknown hacker used Anthropic’s LLM to hack the Mexican government:

The unknown Claude user wrote Spanish-language prompts for the chatbot to act as an elite hacker, finding vulnerabilities in government networks, writing computer scripts to exploit them and determining ways to automate data theft, Israeli cybersecurity startup Gambit Security said in research published Wednesday.

[…]

Claude initially warned the unknown user of malicious intent during their conversation about the Mexican government, but eventually complied with the attacker’s requests and executed thousands of commands on government computer networks, the researchers said.

Anthropic investigated Gambit’s claims, disrupted the activity and banned the accounts involved, a representative said. The company feeds examples of malicious activity back into Claude to learn from it, and one of its latest AI models, Claude Opus 4.6, includes probes that can disrupt misuse, the representative said.

Alternative link here.

Posted on March 6, 2026 at 6:53 AM • View Comments

1 2 3 … 78

Sidebar photo of Bruce Schneier by Joe MacInnis.