The U.S. National Institute of Standards and Technology (NIST) has officially published the final version of its AI Secure Development Framework (AI-SDF). This comprehensive set of voluntary guideline
AIBW Security DeskNeuroHealth AI, a prominent developer of AI-powered diagnostic tools, has disclosed a critical security breach affecting approximately two million patients. Attackers exploited a previously unknown vu
AIBW Security DeskResearchers from Carnegie Mellon University have published a paper detailing a novel jailbreak technique named 'Contextual Triggering.' The attack involves embedding subtle, seemingly benign trigger p
AIBW Security DeskThe non-profit Sentinel AI Foundation has launched ModelGuard, a new open-source framework designed to help developers secure their AI applications. ModelGuard acts as a programmable firewall for Larg
AIBW Security DeskA new paper from Stanford's AI Lab details a novel jailbreaking technique called the 'Recursive Embedding Attack' (REA). This method circumvents the safety alignment of major large language models, in
AIBW Security DeskThe U.S. Cybersecurity and Infrastructure Security Agency (CISA), in partnership with NIST, has issued a new binding operational directive requiring a 'Bill of Materials' for all AI-enabled software p
AIBW Security DeskResearchers at Carnegie Mellon University's CyLab have published a paper detailing a novel jailbreak technique called 'Semantic Inversion.' This method specifically targets multi-modal large language
AIBW Security DeskCognition Labs, the company behind the AI software engineer Devin, has confirmed a significant data breach. Attackers exploited a zero-day vulnerability in an internal API gateway used for data synchr
AIBW Security DeskThe U.S. National Institute of Standards and Technology (NIST) has officially released the AI Red-Teaming Interoperability Framework (ARTIF) 1.0, establishing a standardized methodology for assessing
AIBW Security DeskA new paper published by researchers from Carnegie Mellon University introduces a novel jailbreak technique called 'Semantic Splicing'. The attack bypasses safety filters on multimodal large language
AIBW Security DeskNexus AI, a leading provider of enterprise AI solutions, has confirmed a significant data breach affecting its cloud-based model fine-tuning service. The breach, which occurred in late January 2025, r
AIBW Security DeskThe U.S. National Institute of Standards and Technology (NIST) has officially released version 2.0 of its AI Risk Management Framework (AI RMF 2.0). In a significant policy shift from its predecessor'
AIBW Security Desk