Researchers from Carnegie Mellon University have published a new paper detailing a novel jailbreak technique named 'Contextual Shifting.' The method effectively bypasses state-of-the-art safety alignm
AIBW Security DeskAI video generation startup SynthVerse has disclosed a significant data breach stemming from a misconfigured cloud storage bucket. The exposed dataset contained over 10 million user prompts, associate
AIBW Security DeskThe U.S. Cybersecurity and Infrastructure Security Agency (CISA) has issued a binding operational directive requiring all software vendors providing AI-powered systems to federal agencies for critical
AIBW Security DeskA new paper published by Stanford University's AI Lab details a novel jailbreak technique named 'Contextual Splicing.' This method effectively bypasses the safety alignment of major large language mod
AIBW Security DeskCognition Labs, the creator of the autonomous AI software engineer Devin, has disclosed a significant data breach. The breach exposed a massive dataset containing user prompts, generated code snippets
AIBW Security DeskThe European Parliament has officially passed the 'AI Verifiable, Explainable, and Robust Intelligence Framework (VERIFY) Act', a landmark regulation that extends the EU AI Act's provisions. The new l
AIBW Security DeskA paper published by researchers at Carnegie Mellon University details a novel jailbreak technique named the 'Cognitive Dissonance' attack. Unlike traditional prompt injection methods that rely on tri
AIBW Security DeskNexusAI, a leading platform for enterprise AI model customization, disclosed a critical security breach today. The incident stemmed from a misconfigured cloud storage bucket that left sensitive custom
AIBW Security DeskThe popular open-source AI library LiteLLM was targeted in a sophisticated supply-chain attack via a malicious PyPI package, exposing a critical vulnerability.
AIBW Security DeskThe Open Web Application Security Project (OWASP) has announced the first major release of 'OWASP Guardian,' an open-source framework designed to help developers secure their AI-powered applications.
AIBW Security DeskA new research paper from the Stanford Artificial Intelligence Laboratory (SAIL) introduces a powerful new jailbreak technique named the 'Recursive Embedding Attack.' The method is capable of bypassin
AIBW Security DeskAI safety and research company Anthropic has confirmed a significant security breach affecting its core infrastructure. The incident, attributed to a sophisticated state-sponsored threat actor, result
AIBW Security Desk