AI-generated summary Microsoft researchers have demonstrated that AI agents can be given a hidden backdoor by directly editing fewer than 10 of their neurons. Microsoft says it has not seen any threat actors use the technique and has published guidance on defending against it.
AI-generated summary Railway says that customer AI keys stored on its platform were stolen in an October breach, resulting in an estimated $740,000 in unauthorized usage charges. The company has promised to pay those charges itself when an AI provider will not refund them, and it has filed a complaint with the FBI's IC3.
AI-generated summary Anthropic released Claude Fable 5.2 and Claude Mythos 5.2, models it says show improvements in coding, reasoning, and vision. On CyScenarioBench, Anthropic says Claude Fable 5.2 completed 76.3 percent of challenges compared to 61 percent for OpenAI's GPT-6 Cyber.
AI-generated summary NEAR AI restored its Cloud service following a security incident involving an inference engine vulnerability that exposed internal systems. The company states that an attacker exploited the SGLang flaw to access user information and data from 18 AI agents.
AI-generated summary Fireworks AI expanded its disclosure of an October security incident to report that attackers accessed account and billing information, secrets, datasets, and incomplete model weights for a limited group of customers. Fireworks AI stated that evidence links the activity to a financially motivated cybercriminal group aiming to sell unauthorized LLM access through illicit routing gateways.
AI-generated summary Passwords and API keys typed into approved commands in Claude Code have been exposed in public GitHub repositories. Apiiro reports that 1,122 public copies of a project settings file hold at least one secret following user selections.
AI-generated summary An OpenAI employee accused of placing a hidden recording device in an office entered a not guilty plea in federal court. The plea for Abdulrahman Alfozan was entered Friday during a hearing before Magistrate Judge Peter H. Kang in San Francisco.
AI-generated summary Dario Amodei published an essay titled We Must Pace the Frontier, prompting discussions on artificial intelligence capabilities and governance. Chainguard states that Athena has processed more than 40,000 findings, with 42 percent classified as critical or high across over 500 projects.
AI-generated summary Blockchain analysis firm Chainalysis revealed that an ongoing investigation into an agentic cyber attack exposed names, usernames, password hashes, and live tokens for all users. Chainalysis stated that it took the Know Your Transaction user interface, API, and login page offline while locking impacted accounts and implementing additional monitoring systems.
AI-generated summary A security flaw in Anthropic’s Claude Dispatch enabled a malicious browser extension to execute code on connected computers. Researcher Gal Weizman of Forever Security published findings on November 4, 2026, detailing how the technique bypassed normal user approvals.
AI-generated summary Cybersecurity researchers disclosed a now-patched vulnerability that bypassed Lockdown Mode protections in OpenAI ChatGPT to exfiltrate data. Check Point found a loophole in how popup windows were handled during HTML previews, allowing attackers to escape the sandbox.
AI-generated summary OpenAI previews GPT-6 Cyber, a new cybersecurity AI model that the company says is better at finding vulnerabilities and less likely to hack other platforms. The model is rolling out to select members of OpenAI's Daybreak Red program for authorized defensive cybersecurity work.
AI-generated summary Acronis released a report detailing how a single operator in Taiwan used a team of 12 AI agents to attack hundreds of organizations. The campaign led to the confirmed theft of medical data and personal records across several countries.
The top AI news in your email delivered each morning. Choose categories