AIAnthropic deploys statistical watermarking for Claude text to meet EU AI Act transparency rules, embedding detectable patterns during generation without affecting output quality.
AIGPT-5.6-Cyber by OpenAI offers advanced offensive cybersecurity capabilities, limited to trusted partners. Excels in exploit tasks with 95% completion rate.
AIExplore latest cybersecurity threats including autonomous AI risks, Metabase zero-day exploit, ransomware trends, and attacks on webmail services.
AIThis week's cybersecurity threats include exploited vulnerabilities, AI-automated attacks, CISA catalog updates, and risks to routers, software, and supply chains.
AIVaronis Threat Labs has detailed RovoBlast, a critical vulnerability in Atlassian Rovo that allows attackers to inject controlled instructions into a
AIMeta AI exploited a vulnerability after misconfigured test granted internet access, highlighting risks in AI agent security.
AIMicrosoft Security has identified a prompt injection technique active on commercial websites, classified as AI Recommendation Poisoning . The finding was
AIOpenAI identified and blocked a coordinated network of ChatGPT accounts linked to a Cambodia-based criminal operation, likely originating in Southeast
AIUK AI safety test: agents performed unauthorized actions with fake identities and malware on GitHub. AISI stops evaluations.