AI security firm Robust Intelligence has launched the second major version of its open-source 'AI Firewall.' This framework is designed to be deployed in front of AI applications to provide real-time
AIBW Security DeskA new research paper from Carnegie Mellon University's CyLab has introduced a novel jailbreak technique called 'Model Inversion Cascade' (MIC). The attack leverages a multi-stage process where a serie
AIBW Security DeskCognition AI, the creators of the AI software engineer 'Devin', confirmed a significant security breach. Attackers exploited a zero-day vulnerability in their internal CI/CD pipeline, gaining access t
AIBW Security DeskThe Open Web Application Security Project (OWASP) has officially launched a new open-source project named 'Guardian.' This framework is designed to standardize and automate the process of security tes
AIBW Security DeskCognition AI, a leading developer of enterprise-grade LLMs, confirmed a significant data breach after attackers exploited a misconfigured cloud storage bucket. The breach resulted in the exfiltration
AIBW Security DeskIn a significant move to enhance transparency and security, the European Union's AI Office has invoked new powers under the AI Act to mandate an 'AI Bill of Materials' (AIBOM) for all systems classifi
AIBW Security DeskA new paper from Carnegie Mellon University's CyLab has detailed a novel jailbreak technique named 'Recursive Obfuscation'. The attack bypasses the safety alignment of major large language models, inc
AIBW Security DeskCognition Labs, the company behind the AI software engineer 'Devin', has announced a significant security breach that occurred in late January 2025. According to their official statement, unauthorized
AIBW Security DeskThe White House has issued a landmark Executive Order on AI security, establishing mandatory standards for AI systems deployed in critical infrastructure. The order, titled the 'AI System Resilience a
AIBW Security DeskA paper published by Stanford University's AI Lab details a novel jailbreak technique named 'Cognitive Override.' This method exploits the advanced reasoning pathways in frontier large language models
AIBW Security DeskA new research paper from the Stanford AI Lab details a powerful jailbreak technique named 'Cognitive Jigsaw.' The attack works by splitting a malicious request into multiple, seemingly benign and log
AIBW Security DeskA sophisticated threat actor successfully breached Cognition Labs, the creators of the AI software engineer 'Devin'. The attackers employed a novel 'model inversion' technique, not against a standard
AIBW Security Desk