Researchers at Carnegie Mellon University have published a paper detailing a novel and highly effective jailbreaking technique called 'Many-Shot Jailbreaking'. Unlike previous methods that rely on spe
AIBW Security DeskThe United States government has enacted the 'Foundational Model Accountability Act of 2025' (FMAA), a landmark piece of legislation aimed at regulating the development of powerful AI systems. The act
AIBW Security DeskA new paper from researchers at the Carnegie Mellon AI Safety Institute (CMU-ASI) details a novel jailbreak technique named 'Semantic Morphing'. This method is capable of consistently bypassing the sa
AIBW Security DeskProminent AI research lab Aether AI has confirmed a significant security breach, resulting in the unauthorized access and exfiltration of sensitive data. The attackers, identified as the 'ShadowNet' s
AIBW Security DeskThe Open Web Application Security Project (OWASP) has officially launched AI Sentinel, a new open-source framework designed to help developers and security professionals test the security of applicati
AIBW Security DeskA new research paper published by security researchers at Carnegie Mellon University has detailed a novel jailbreak technique named 'Chroma-Shift.' This multimodal attack bypasses the safety filters o
AIBW Security DeskNexus AI, a leading provider of enterprise-grade language models, has confirmed a critical data breach that exposed over 15 million user prompts and a significant portion of its proprietary fine-tunin
AIBW Security DeskIn a landmark policy development, the United States and the European Union jointly announced the "Transatlantic AI Safety Accord." This new regulation mandates rigorous, independent third-party audits
AIBW Security DeskSynthVerse AI, a prominent provider of generative image and video APIs, disclosed a significant data breach affecting its core cloud infrastructure. The attackers exploited a misconfigured Kubernetes
AIBW Security DeskA joint research paper from Stanford and MIT Lincoln Laboratory details a novel jailbreak technique named the "Recursive Embedding Attack." The method involves crafting prompts that embed harmful inst
AIBW Security DeskThe European Union's AI Act has officially entered its first enforcement phase, with the newly established EU AI Board beginning active audits of high-risk AI systems deployed within the member states
AIBW Security DeskProminent AI startup Cognition AI announced a significant security breach that resulted in the exfiltration of sensitive intellectual property and user data. According to the company's disclosure, an
AIBW Security Desk