The European Union's AI Office has announced a significant update to the AI Act's implementation guidelines, introducing a mandatory 'AI Bill of Materials' (AIBOM) for all high-risk AI systems deploye
Researchers at the Stanford AI Lab (SAIL) have published a paper detailing a new jailbreak technique called 'EchoJailbreak,' which effectively circumvents the safety alignments of leading multi-modal
Cognition AI, the creators of the popular 'Synapse' code generation model, disclosed a severe security breach that occurred in late February 2025. Attackers exploited a zero-day vulnerability in a thi
The European Union has officially passed the AI Model Security and Accountability Act (AMSAA), creating a comprehensive regulatory framework for AI security. The legislation mandates stringent securit
A new research paper from Carnegie Mellon University's CyLab introduces a novel jailbreak technique named 'Semantic Splicing'. This method circumvents the safety filters of leading Large Language Mode
Emerging AI leader CognitionAI confirmed a significant security breach today, resulting in the exfiltration of core intellectual property. Attackers, believed to be a sophisticated state-sponsored gro
The United States Congress has passed the landmark 'AI Deployment and Responsibility Act' (AIDA), establishing a new federal framework for the security and safety of high-risk AI systems. Effective Ja
A paper published by researchers at the Cyberspace Security Institute (CSI) details a novel jailbreak technique called 'Semantic Splicing.' This attack bypasses the safety alignment of major large lan
Global tech giant CogniSys has confirmed a critical security incident involving its flagship product, the Aura AI Assistant. Attackers exploited a previously unknown zero-day vulnerability in Aura's e
The Open Web Application Security Project (OWASP) has launched 'Guardian,' a new open-source framework aimed at helping organizations secure their entire AI/ML development lifecycle. Guardian provides
Cognition AI, a leading developer of enterprise-grade language models, disclosed a severe security breach originating from a misconfigured cloud storage bucket. Attackers gained access to and exfiltra
AI security startup Aperture Security has released 'Rebuff', a new open-source tool designed to help developers protect Large Language Model (LLM) applications from prompt injection attacks. The Pytho