Anthropic said its Claude-based security models gained unauthorized access to the sensitive production environments of three outside organizations during internal testing designed to measure the models’ offensive cyber capabilities.

The events, which Anthropic revealed Thursday, are the second revelation in 10 days that AI models from the world’s wealthiest providers have trespassed into protected networks, an offense that, in more traditional hacking scenarios, could land the human behind the keyboard in prison for years. Earlier this month, OpenAI said its security models exploited a zero-day vulnerability for use in breaking into the network of Hugging Face, a platform for open source machine-learning models and AI datasets. The OpenAI models went on to steal access credentials and other confidential Hugging Face information. The OpenAI models also exploited publicly exposed credentials to compromise accounts of four other third-party services.

Anthropic said the OpenAI event spurred its engineers to review similar cybersecurity evaluations by Claude models. The audit found three incidents “in which a model accessed the internet from within or while interacting with the evaluation environment of Irregular, one of our third-party evaluation partners, and then gained unauthorized access to the production infrastructure of three different organizations.”

Read full article

Comments

With Chrome, Google pioneered the rapid release model for browser security. Now, Google says updates may need to change in the face of AI security analysis. According to the company, the number of bug fixes in Chrome releases has skyrocketed in recent months because AI is detecting so many flaws. We could be looking at more frequent updates soon, but Google is also working on ways to get those updates rolled out without bothering you as much.

Google has released two major Chrome milestone builds recently—Chrome 149 in early June and Chrome 150 just a few weeks later. These two updates had a total of 1,072 bug fixes, which is more than the previous 23 releases combined. Such is the impact of giant cybersecurity AI models that can probe software for vulnerabilities at light speed. Some of these vulnerabilities were serious, too, with one bug hiding in the Chrome codebase for 13 years. If it had been exploited, an attacker could have bypassed the Chrome sandbox to make the browser access local files.

With the vastly higher rate of vulnerability identification, Google is worried bad actors will also be able to identify software flaws faster. Its goal is to ensure your Chrome install is always up to date or as close to it as possible. The first step toward that is the two-week update cycle the company announced earlier in 2026, but it's now piloting a system that would update Chrome twice per week. This would get patches out the door faster, ensuring that browsers are ready for the threat of AI-fueled attacks.

Read full article

Comments

Microsoft is introducing new AI tools designed to help customers continuously streamline and automate the process of identifying and reducing their exposure to security risks.

The new tools come less than a week after OpenAI lost control of two of its security models when they infiltrated the servers of startup Hugging Face. The hack, Hugging Face added, involved “a swarm of tens of thousands of automated actions” that stole internal Hugging Face credentials. The OpenAI models achieved this feat by exploiting a zero-day flaw in Hugging Face’s data-processing pipeline to run malicious code that escalated the models’ access to the company’s high-value cloud and server clusters.

Microsoft’s announcements on Monday made no reference to the event, which OpenAI said was “unprecedented.” The company also didn’t say what would prevent the new tools from similarly going rogue.

Read full article

Comments

Earlier this month, Anthropic said its Mythos Preview model was so good at finding cybersecurity vulnerabilities that the company was limiting its initial release to "a limited group of critical industry partners." Since then, debate has raged over whether the model presages an era of turbocharged AI-aided hacking or if Anthropic is just building hype for what is a relatively normal step up on the ladder of advancing AI capabilities.

Mozilla added some important data to that debate Tuesday, writing in a blog post that early access to Mythos Preview had helped it pre-identify 271 security vulnerabilities in this week's release of Firefox 150. The results were significant enough to get Firefox CTO Bobby Holley to enthuse that, in the never-ending battle between cyberattackers and cyberdefenders, "defenders finally have a chance to win, decisively."

"We've rounded the curve"

Holley didn't go into detail on the severity of the hundreds of vulnerabilities that Mythos reportedly detected simply by analyzing the unreleased source code of Firefox's latest version. But by way of comparison, he noted that Anthropic's Opus 4.6 model found only 22 security-sensitive bugs when analyzing Firefox 148 last month.

Read full article

Comments

Last week, Anthropic announced it was restricting the initial release of its Mythos Preview model to "a limited group of critical industry partners," giving them time to prepare for a model that it said is "strikingly capable at computer security tasks." Now, the UK government's AI Security Institute (AISI) has published an initial evaluation of the model's cyberattack capabilities that adds some independent public verification to those Anthropic reports.

AISI's findings show that Mythos isn't significantly different from other recent frontier models in tests of individual cybersecurity-related tasks. But Mythos could set itself apart from previous models through its ability to effectively chain these tasks into the multistep series of attacks necessary to fully infiltrate some systems.

"The Last Ones" finally falls

AISI has been putting various AI models through specially designed Capture the Flag challenges since early 2023, when GPT-3.5 Turbo struggled to complete any of the group's relatively low-level "Apprentice" tasks. Since then, the performance of subsequent models has risen steadily, to the point where Mythos Preview can complete north of 85 percent of those same Apprentice-level CTF tasks.

Read full article

Comments

Over the last few months, tools like OpenClaw have shown what tech-savvy AI users can do by setting a virtual cadre of automated agents on a task. But that individual convenience can be a DDOS-level pain for online service providers faced with a torrent of Sybil attack-style requests from thousands of such agents at once.

Identity startup World thinks its "proof of human" World ID technology can provide a potential solution to this problem. Today, the company launched a beta of Agent Kit, a new way for humans to prove they are directing their AI agents and for websites to limit access to AI agents working on behalf of an actual human.

If you recognize the name World, it's probably as the organization behind WorldCoin, the Sam Altman-founded cryptocurrency outfit that launched in 2023 alongside an offer to give free WorldCoin to anyone who scanned their iris in a physical "orb". While WorldCoin still exists (at a current value well below its early 2024 peaks), World has now pivoted to focus on World ID, which uses the same iris-scanning technology as the basis for a cryptographically secure, unique online identity token stored on your phone.

Read full article

Comments

On Thursday, a team of researchers led by Microsoft announced that they had discovered, and possibly patched, what they're terming a biological zero-day—an unrecognized security hole in a system that protects us from biological threats. The system at risk screens purchases of DNA sequences to determine when someone's ordering DNA that encodes a toxin or dangerous virus. But, the researchers argue, it has become increasingly vulnerable to missing a new threat: AI-designed toxins.

How big of a threat is this? To understand, you have to know a bit more about both existing biosurveillance programs and the capabilities of AI-designed proteins.

Catching the bad ones

Biological threats come in a variety of forms. Some are pathogens, such as viruses and bacteria. Others are protein-based toxins, like the ricin that was sent to the White House in 2003. Still others are chemical toxins that are produced through enzymatic reactions, like the molecules associated with red tide. All of them get their start through the same fundamental biological process: DNA is transcribed into RNA, which is then used to make proteins.

Read full article

Comments

Starting today, Google is implementing a change that will enable its Gemini AI engine to interact with third-party apps, such as WhatsApp, even when users previously configured their devices to block such interactions. Users who don't want their previous settings to be overridden may have to take action.

An email Google sent recently informing users of the change linked to a notification page that said that “human reviewers (including service providers) read, annotate, and process” the data Gemini accesses. The email provides no useful guidance for preventing the changes from taking effect. The email said users can block the apps that Gemini interacts with, but even in those cases, data is stored for 72 hours.

No, Google, it’s not good news

The email never explains how users can fully extricate Gemini from their Android devices and seems to contradict itself on how or whether this is even possible. At one point, it says the changes “will automatically start rolling out” today and will give Gemini access to apps such as WhatsApp, Messages, and Phone “whether your Gemini apps activity is on or off.” A few sentences later, the email says, “If you have already turned these features off, they will remain off.” Nowhere in the email or the support pages it links to are Android users informed how to remove Gemini integrations completely.

Read full article

Comments

"A threshold has been reached. We are effectively being DDoSed. If we could, we would charge them for this waste of our time," wrote Daniel Stenberg, original author and lead of the curl project, on LinkedIn this week.

Curl (cURL in some realms), which turned 25 years old in 2023, is an essential command-line tool and library for interacting with Internet resources. The open source project receives bug reports and security issues through many channels, including HackerOne, a reporting service that helps companies manage vulnerability reporting and bug bounties. HackerOne has fervently taken to AI tools in recent years. "One platform, dual force: Human minds + AI power," the firm's home page reads.

Stenberg, saying that he's "had it" and is "putting my foot down on this craziness," suggested that every suspected AI-generated HackerOne report will have its reporter asked to verify if they used AI to find the problem or generate the submission. If a report is deemed "AI slop," the reporter will be banned. "We still have not seen a single valid security report done with AI help," Stenberg wrote.

Read full article

Comments

Spammers used OpenAI to generate messages that were unique to each recipient, allowing them to bypass spam-detection filters and blast unwanted messages to more than 80,000 websites in four months, researchers said Wednesday.

The finding, documented in a post published by security firm SentinelOne’s SentinelLabs, underscores the double-edged sword wielded by large language models. The same thing that makes them useful for benign tasks—the breadth of data available to them and their ability to use it to generate content at scale—can often be used in malicious activities just as easily. OpenAI revoked the spammers’ account in February.

“You are a helpful assistant”

The spam blast is the work of AkiraBot—a framework that automates the sending of messages in large quantities to promote shady search optimization services to small- and medium-size websites. AkiraBot used python-based scripts to rotate the domain names advertised in the messages. It also used OpenAI’s chat API tied to the model gpt-4o-mini to generate unique messages customized to each site it spammed, a technique that likely helped it bypass filters that look for and block identical content sent to large numbers of sites. The messages are delivered through contact forms and live chat widgets embedded into the targeted websites.

Read full article

Comments

A little over two weeks ago, a largely unknown China-based company named DeepSeek stunned the AI world with the release of an open source AI chatbot that had simulated reasoning capabilities that were largely on par with those from market leader OpenAI. Within days, the DeepSeek AI assistant app climbed to the top of the iPhone App Store's "Free Apps" category, overtaking ChatGPT.

On Thursday, mobile security company NowSecure reported that the app sends sensitive data over unencrypted channels, making the data readable to anyone who can monitor the traffic. More sophisticated attackers could also tamper with the data while it's in transit. Apple strongly encourages iPhone and iPad developers to enforce encryption of data sent over the wire using ATS (App Transport Security). For unknown reasons, that protection is globally disabled in the app, NowSecure said.

Basic security protections MIA

What’s more, the data is sent to servers that are controlled by ByteDance, the Chinese company that owns TikTok. While some of that data is properly encrypted using transport layer security, once it's decrypted on the ByteDance-controlled servers, it can be cross-referenced with user data collected elsewhere to identify specific users and potentially track queries and other usage.

Read full article

Comments