The OWASP Foundation has released a new open-source tool called 'ModelGuard' aimed at helping developers secure their Large Language Model (LLM) applications. Designed for integration into CI/CD pipel
AI startup Cognition Labs announced a significant security breach affecting its autonomous AI software agent, Devin. Threat actors exploited a misconfigured API gateway, gaining unauthorized access to
AI voice-cloning startup SynthVoice Inc. has disclosed a critical security breach affecting over five million users. Attackers exploited a vulnerability in an open-source MLOps orchestration tool used
Researchers from Carnegie Mellon University have published a paper detailing 'MindWipe,' a novel and highly effective jailbreak technique. The method uses a combination of adversarial Unicode sequence
The European Parliament has officially passed the AI Red-Teaming Act (ARTA), a landmark piece of legislation designed to bolster the security of high-risk artificial intelligence systems operating wit
In a landmark policy move, a joint U.S.-EU task force has announced the AI Secure Deployment Act (ASDA), which mandates compulsory third-party security audits for all foundational models and AI system
NexusAI, a leading developer of foundational models, confirmed today it suffered a sophisticated data breach. Attackers exploited a zero-day vulnerability in a third-party data processing library used
The U.S. AI Safety Institute (USAISI), under the Department of Commerce, has released its first major deliverable: the 'GARLAND' framework. GARLAND (Generative AI Red-teaming and Layered Analysis for
Researchers at the Stanford Artificial Intelligence Laboratory (SAIL) have published a groundbreaking paper detailing a novel jailbreak technique named the 'Recursive Embedding Attack' (REA). The atta
AuraAI, a leading AI research lab, confirmed a major security breach resulting in the exfiltration of the proprietary model weights for their upcoming flagship model, 'Aura-5-Pro'. The attack, attribu
Following the AI Safety Summit in Seoul, G7 member nations have formally ratified the 'AI Red-Teaming and Auditing Accord' (ARTAA), establishing the first international mandatory security audit framew
A new research paper published by academics at Stanford University details a novel jailbreak technique named 'Cognitive Dissonance Attack' (CDA). This method successfully bypasses the safety alignment