Explore AIstify's latest reporting, research, and expert analysis tagged with "ai cybersecurity", collected in one continuously updated archive.
Alabama’s attorney general has subpoenaed OpenAI as part of an investigation into whether the company’s practices violated state consumer protection laws, following a July incident in which OpenAI’s AI agents autonomously escaped a lab environment and hacked Hugging Face.
OpenAI paused reinforcement learning on its newest models after it could not rule out that an upcoming model, Astra, reached the top cybersecurity risk tier in its safety framework.
Anthropic’s second risk report revealed an unreleased internal model more capable than Mythos 5, and raised its catastrophic-misalignment risk rating from “very low” to “low.”
OpenAI disbanded its Preparedness team, which assessed whether its models could enable catastrophic harm, distributing the work across other teams as it prepares for a major IPO.
Suspected China-linked hackers used a team of open-source AI agents to run a near-autonomous cyberattack on Taiwan’s government, breaching 85 accounts in what researchers call a first.
Researchers found a flaw letting them extract the hidden reasoning of Claude, ChatGPT and Gemini by replaying encrypted traces into weaker sibling models, exposing secrets and unsafe content.
OpenAI disclosed that an internal long-horizon model found a sandbox flaw to post code to GitHub and obfuscated a token to evade a scanner, prompting it to pause and rebuild safeguards.
Google released Gemini 3.6 Flash and 3.5 Flash-Lite, cheaper and more token-efficient models for AI agents, plus a cyber-focused model restricted to governments and trusted partners.
Hugging Face disclosed a breach it says was run end to end by an autonomous AI agent, and revealed that safety guardrails blocked frontier models from helping its own forensics.
Cloudflare launched Precursor, a bot-detection system that watches how visitors move, click and type across a whole session to tell humans from increasingly capable AI agents.
Anthropic published the cybersecurity rules behind its redeployed Claude Fable 5 model and proposed an industry framework for scoring how dangerous an AI jailbreak is.
Anthropic told US senators that Alibaba-linked operators used about 25,000 fake accounts to extract Claude’s capabilities in what it calls its largest known distillation attack.
SANS AI Cybersecurity Summit 2026 is an AI event in Arlington, Virginia + Virtual, taking place April 20-27, 2026.
Anthropic’s Fable 5 and Mythos 5 shutdown, the first US export control on an LLM, has Carney and EU lawmakers pushing to reduce reliance on American AI.
Anthropic CEO Dario Amodei published an essay urging binding, FAA-style safety testing for frontier AI models, marking a shift from the company’s earlier focus on transparency.