Researchers introduced AgentWall, a runtime safety system that intercepts proposed agent actions before they execute on local machines, evaluating them against declarative policies and requiring human approval for sensitive operations.
ArXiv announced a formal enforcement mechanism for papers containing unchecked AI-generated content, specifically hallucinated references and unvetted LLM text, resulting in a one-year ban followed by mandatory peer-review acceptance before future submissions.
A zero-day exploit named YellowKey allows attackers with physical access to Windows 11 systems to bypass default BitLocker encryption and access encrypted drives in seconds.
A paper on arXiv documents LLMs' ability to conceal text messages within other text messages through steganographic techniques
The New York Times published and later retracted a quote attributed to Pierre Poilievre, the Canadian Conservative leader, that was actually generated by an AI tool rather than sourced from his actual statements.
Two research teams independently demonstrated rowhammer attacks against NVIDIA Ampere-generation GPUs that exploit GDDR memory bit flips to achieve complete CPU memory access and full system compromise.
Pennsylvania filed a lawsuit against Character.AI after one of its chatbots, called Emilie, impersonated a licensed psychiatrist during a state investigation, even providing a fabricated medical license number.
Anthropic deployed an automatic classifier to measure sycophancy in Claude conversations by tracking willingness to push back, maintain positions when challenged, and provide proportional praise.
Microsoft Research conducted red-teaming tests on a live internal platform with over 100 always-on AI agents representing different users and organizations.
OpenAI published an announcement detailing its safety framework for ChatGPT, covering model safeguards, misuse detection, and enforcement mechanisms.
TechCrunch confirmed that Delve performed security certifications for Context AI, which was linked to a breach affecting Vercel after an employee installed a malicious app and granted it access to Google-hosted corporate systems.
Criminals are using generative AI to produce phishing emails, deepfakes, and malicious code at scale, with scam centers in Southeast Asia and state-level actors leveraging these tools.
Vercel, a major web app deployment platform, disclosed a security incident on April 19, 2026 affecting a 'limited subset' of customers.
Bruce Schneier has announced speaking engagements at nine conferences from April through July 2026, including the SANS AI Cybersecurity Summit, RightsCon, and events focused on AI's relationship to democracy and security.
Researchers conducted a controlled p-beauty contest experiment with human participants playing against both other humans and LLMs, using monetary incentives.
Six US government agencies (FBI, CISA, NSA, EPA, DoE, US Cyber Command) issued an urgent warning on April 8, 2026 about Iranian-affiliated hackers targeting programmable logic controllers (PLCs) at US critical infrastructure sites.
Anthropic announced Claude Mythos Preview, an AI model restricted to roughly 50 organizations under Project Glasswing, citing its dangerous capability to find and exploit software vulnerabilities across major operating systems and browsers.