The AI Village, a prominent AI security community, has released Gorgon Scanner, a powerful open-source tool for automated security testing of AI applications. Gorgon is designed to help developers and
AIBW Security DeskA paper published by researchers at the Stanford AI Lab details a novel jailbreak technique named 'Contextual Hijacking.' The attack circumvents the safety alignment of major large language models by
AIBW Security DeskLeading AI firm SynthWeaver AI disclosed a severe security breach that occurred in late February. Attackers leveraged a sophisticated spear-phishing campaign to gain an initial foothold, eventually co
AIBW Security DeskIn a landmark move for AI governance, the United States and the European Union have jointly announced the 'AI Model Accountability Act.' This new legislation mandates stringent security and safety pro
AIBW Security DeskA new paper from the Stanford AI Lab has introduced a sophisticated jailbreak technique named 'Cognitive Jigsaw.' The attack bypasses the safety filters of leading Large Language Models (LLMs) by dist
AIBW Security DeskNexusAI, a leader in generative AI for enterprise, confirmed a catastrophic security breach today. Attackers gained unauthorized access to their core infrastructure, exfiltrating terabytes of sensitiv
AIBW Security DeskThe United States and the European Union have jointly announced the Trans-Atlantic AI Security Framework (TAISF), a landmark policy agreement aimed at standardizing AI security practices for critical
AIBW Security DeskResearchers from Carnegie Mellon University have published a paper detailing a novel jailbreak technique named 'Semantic Jitter.' The attack circumvents safety alignments in leading large language mod
AIBW Security DeskLeading AI startup NexusAI has disclosed a severe security breach resulting in the exfiltration of core intellectual property. Attackers successfully infiltrated their cloud environment, gaining acces
AIBW Security DeskThe U.S. Department of Commerce, through the National Institute of Standards and Technology (NIST), has finalized its 'AI Trustmark' framework, establishing mandatory safety and security standards for
AIBW Security DeskCognition Labs, the company behind the AI software engineer 'Devin', has announced a significant security breach. Attackers exploited a vulnerability in a third-party library used for managing Git aut
AIBW Security DeskResearchers at Carnegie Mellon University have published a paper detailing a novel jailbreak technique called 'Model Inversion'. This method exploits subtle information leakage in the logit outputs of
AIBW Security Desk