Researchers from Carnegie Mellon University have published a paper detailing 'GlyphJail,' a novel jailbreak technique effective against several state-of-the-art large language models, including those
Cognition AI, a leading provider of enterprise-grade large language models, disclosed a significant security breach that occurred in late May 2026. Attackers exploited a misconfigured cloud storage bu
The AI security startup ProtectAI has launched GuardRail, an open-source firewall specifically designed to protect applications built on Large Language Models (LLMs). GuardRail acts as an intermediary
SynthesisAI, a prominent provider of AI-generated synthetic data for training computer vision models, has disclosed a significant security breach. Attackers gained unauthorized access to the company's
Researchers from a leading university have published a paper detailing a novel jailbreak technique called the "Multi-Step Contextual Attack" (MSCA). Unlike single-prompt attacks, MSCA involves a serie
The White House has unveiled the 'Securing Foundational AI with Uniform Regulations and Audits Act' (AI SECURE Act), a landmark piece of legislation aimed at mitigating risks from powerful AI models.
The White House has issued an executive order mandating the use of standardized 'AI Nutrition Labels' for any artificial intelligence system procured or developed by federal agencies. Effective immedi
Healthcare technology firm SynthHealth AI has disclosed a catastrophic data breach affecting approximately 15 million patients. Attackers exploited a vulnerability in the company's publicly accessible
Anthropic just open-sourced a new framework that uses AI models to find critical code vulnerabilities, achieving a stunning 50% success rate on difficult test cases—a 10x improvement over baseline tools.
The Open Web Application Security Project (OWASP) has officially launched GuardianML, a comprehensive open-source framework designed to help organizations secure their end-to-end machine learning pipe
Researchers from the Stanford AI Lab have published a groundbreaking paper detailing a new jailbreak technique named 'Cognitive Jigsaw.' This method circumvents state-of-the-art safety filters in larg
A paper published by researchers at ETH Zurich details a novel attack technique called 'Semantic Doppelgänger'. This method successfully bypasses the safety filters of leading multimodal AI models lik