The Aoki infostealer, also known as Aokigahara, has expanded its collection capabilities to steal credentials and session files from AI coding assistants,…
Tag: AI Security
Stolen AI API keys are paying for hackers’ autonomous scans
A seller on a restricted criminal forum is marketing an autonomous hacking tool that runs on stolen OpenAI, Anthropic and Google API keys, so the key’s…
AI worms could spread across your smart devices, Anthropic warns
Researchers say small AI models could be capable of spreading across vulnerable smart devices within months.
Small Agents, Smaller Blast Radius: Controlling What AI Can Do, (Fri, Oct 16th)
I believe the cybersecurity industry may be approaching AI security the wrong way.
AI Slop Isn’t Just for Social Media; It’s Ruining Cyberattacks, Too
Don’t buy the hype! AI has been dumbing down cyberattacks, and serious threat actors are barely touching it.
Android gets AI defenses against messaging scams, fake calls
Google announced new AI-powered defenses against scam messages and call-forwarding abuse on Android, currently rolling out to eligible devices. […]
Think Before You Click: Phishing in the AI Era
AI is making phishing more convincing and scalable, requiring employees to verify identity and context instead of relying on familiar warning signs.
Senators press Trump admin to rally federal government around AI safety, security
The letter argues federal agencies should more rigorously test AI models for security threats and sandbox evasion, set new safety standards and lean into…
The next election influence campaign will target your AI chatbot
Someone is seeding the internet with hyperlocal content about political races. Researchers say it’s designed to train AI chatbots to favor candidates…
Critical ChatGPT GitHub Connector Flaw Could Allow Attackers to Steal Private Repository Secrets
A critical flaw in ChatGPT’s GitHub integration has the potential to turn a routine repository review into a secret-theft attack. A report published on…
Anthropic Warns AI Worms Could Soon Spread Across IoT Devices
Small artificial intelligence models could soon be able to freely replicate across internet devices, forming botnets that do not require centralized…
The Future of AI Cryptanalysis
Matthew Green has been writing a rather pessimistic series of posts about the potential for AI systems to vastly outperform humans in cryptanalysis of…
FTC Demands Answers From OpenAI and Anthropic About AI Safety
The FTC has subpoenaed OpenAI and Anthropic over potential consumer protection violations. An AI security expert explains the risks of enterprise AI…
CrowdStrike and Anthropic Give Critical Infrastructure Defenders the AI Advantage
This post has no text preview — click the link below to read the original article. This article has been indexed from Blog Read the original article: CrowdStrike and Anthropic Give Critical Infrastructure Defenders the AI Advantage
OpenAI’s Hidden Recorder Case: How AI Helped Investigators
OpenAI says AI helped investigate a hidden recording device. The case highlights insider threats and why sensitive meetings need physical security checks.
Anthropic warns small AI models could self-replicate through IoT devices
“Small weight-based replicators” could usher in a new generation of computer worms.
Internet exposure of AI tools, ICS devices continues to grow
Vulnerability disclosures and hacking campaigns haven’t made much of a dent in the amount of important infrastructure left online, a new report found.
AI infrastructure spending forecast to outstrip revenue
AI infrastructure providers face a looming financial crisis as capital expenditures are projected to vastly exceed revenue generation through 2030,…
Sophos AI Research on Calibrating SOC Agents
Sophos AI researchers have developed a calibration system to identify errors made by AI agents used in security operations centers (SOCs).
AI Agents Build Chrome Zero-Day Exploit in Six Days, Winning $250,000 Reward
AI-powered security agents developed a Google Chrome exploit within six days and earned XBOW company $250,000 from Google. The exploit involved an…