A paper published by researchers at Carnegie Mellon University details a novel jailbreak technique named 'Semantic Obfuscation' that has proven effective against the safety filters of leading AI model
The U.S. National Institute of Standards and Technology (NIST) has officially released the AI Secure Development Framework (AI-SDF), a landmark set of guidelines for federal agencies procuring and dep
Researchers at Carnegie Mellon University's CyLab have published a paper detailing a novel jailbreak technique named the 'Recursive Embedding Attack' (REA). This method circumvents the safety alignmen
Nexus AI, a leading provider of enterprise AI solutions, confirmed a major security breach that resulted in the exfiltration of several proprietary large language model weights and a database containi
The European Parliament has officially passed the 'AI Trust & Transparency Act' (ATTA), a landmark piece of legislation aimed at governing the development and deployment of AI systems within the EU. A
A new paper from Stanford University researchers introduces 'Chameleon,' a novel jailbreak technique targeting multi-modal Large Language Models (LLMs). The method bypasses safety filters by embedding
AI solutions provider SynthAI announced a significant data breach today, exposing sensitive information from over five million user accounts. The breach was traced back to a misconfigured cloud storag
The DEF CON AI Village has officially launched 'ModelGuard', a new open-source security framework aimed at helping developers and security teams proactively test their AI applications. Released on Git
In a significant move towards global AI governance, the G7 nations have formally announced the 'Kyoto AI Security Framework.' This binding agreement establishes a set of mandatory safety and security
Healthcare technology firm OmniHealth AI disclosed a critical data breach that exposed the sensitive records of approximately 2.5 million patients. The breach originated from a misconfigured API endpo
A team from Carnegie Mellon University published a paper detailing a sophisticated new jailbreak technique named 'Cognitive Override.' This method bypasses the safety filters of leading large language
The Open Web Application Security Project (OWASP) has released GARNET (Generative AI Red-Teaming Network), a new open-source framework aimed at standardizing security testing for AI applications. GARN