A new research paper from Carnegie Mellon University's CyLab has introduced a novel jailbreak technique named 'Semantic Splicing'. Unlike traditional prompt injection attacks that rely on clever wordi
Enterprise AI leader Cognito Systems has disclosed a critical security breach that occurred in late January 2025. Attackers exploited a zero-day vulnerability in a popular MLOps data orchestration too
The United States government has signed into law the 'AI Transparency, Reporting, and Universal Safety Testing (TRUST) Act.' This landmark legislation establishes a new regulatory framework for compan
AI startup SynthAI has disclosed a major security breach where attackers exploited a vulnerability in their MLOps pipeline, gaining access to core infrastructure. The breach resulted in the exfiltrati
In a landmark move for AI regulation, the U.S. National Institute of Standards and Technology (NIST) and the EU's Agency for Cybersecurity (ENISA) have announced the 'AI Trust Framework'. This joint p
Emerging AI startup Chroma AI disclosed a critical security breach that occurred in late January. Attackers exploited a vulnerability in a third-party CI/CD pipeline tool to gain access to the company
A team using GPT-4 solved 79% of challenges at a top cybersecurity contest, placing 35th out of 725 teams. This breakthrough shows AI automating complex hacking tasks, questioning the future of human-only security competitions. What does this mean for cybersecurity training?
Emerging AI leader SynthVerse AI confirmed a critical security breach that resulted in the exfiltration of both sensitive user data and the proprietary model weights for its upcoming flagship generati
A new research paper published by Stanford University's AI Lab details a novel jailbreak technique named 'Cognitive Dissonance'. The attack exploits the logical reasoning capabilities of large languag
NVIDIA has announced the release of NeMo Guardrails 2.0, a major update to its open-source toolkit for building trustworthy and secure LLM-powered applications. This new version introduces several ent
Cognition AI, the firm behind the popular autonomous coding agent Devin, has confirmed a critical security breach that resulted in the exfiltration of gigabytes of sensitive internal data. The breach,
The SentinelAI Foundation has announced the general availability of LLM-Guard v2.0, a major update to its open-source security toolkit for AI applications. LLM-Guard acts as a self-hostable firewall t