OpenAI has launched GPT-5.5 and a specialized GPT-5.5-Cyber model, granting vetted security experts powerful new tools to accelerate vulnerability research. This expansion of the Trusted Access for Cyber program aims to fortify defenses against emerging AI-powered threats. What does this mean for the future of cybersecurity?
AIBW Security DeskMajor AI developer Cognition AI has confirmed a significant security breach originating from a compromised third-party data processing library within their MLOps pipeline. Attackers successfully exfil
AIBW Security DeskThe United States government has announced the 'AI Transparency, Responsibility, and Usability in Society (TRUST) Act', a landmark piece of legislation aimed at regulating the security of high-risk AI
AIBW Security DeskAI security startup Metropolis AI has launched 'Guardian', an open-source framework designed to provide real-time protection for applications powered by large language models. Guardian acts as a model
AIBW Security DeskA new research paper from Carnegie Mellon University's CyLab introduces 'Semantic Splicing,' a novel jailbreak technique effective against the latest generation of large language models, including GPT
AIBW Security DeskAdept AI, a leading applied AI company, disclosed a severe security breach that resulted in the exfiltration of proprietary model weights for its upcoming multimodal agent, 'Foresight-2'. Attackers, b
AIBW Security DeskThe U.S. National Telecommunications and Information Administration (NTIA), in collaboration with the Cybersecurity and Infrastructure Security Agency (CISA), has finalized the AI Vulnerability and Di
AIBW Security DeskResearchers from Carnegie Mellon University have published a paper detailing a novel jailbreak technique named 'Glyph-Jailbreak'. This method bypasses the safety alignment of leading large language mo
AIBW Security DeskNexus AI revealed a sophisticated supply chain attack targeting its flagship 'Aethel' large language model. Attackers, believed to be state-sponsored, gained access to the company's data curation pipe
AIBW Security DeskThe U.S. AI Safety Institute Consortium (AISIC), in collaboration with international partners, has released the first version of the 'SecureAI Framework,' a comprehensive, standardized methodology for
AIBW Security DeskA paper published by researchers at the Stanford AI Lab details a novel jailbreak technique named 'Contextual State Corruption' (CSC). Unlike previous methods that rely on single-turn prompt injection
AIBW Security DeskNexusAI, a leading AI research firm, has confirmed a catastrophic security breach resulting in the exfiltration of their flagship proprietary model, 'Helios-5', and several petabytes of its curated tr
AIBW Security Desk