AI security is now a core part of cybersecurity. In AIstify’s AI Security section, we cover how models are attacked, defended, and operated safely – from prompt injection and data leakage to supply-chain risk and model misuse. We track vendor tooling, red-teaming, evaluations, and the policies shaping secure deployment across cloud and edge. Whether you are defending systems or building them, this hub keeps you current on threats, mitigations, and the standards emerging around trustworthy AI.
Anthropic released a new security plugin for Claude Code that reviews AI-generated code for vulnerabilities while it is being written. The system uses a separate Claude instance to scan changes in the background and automatically suggest fixes before code reaches pull requests.
Anthropic says its unreleased Mythos AI model has identified more than 10,000 high- and critical-severity software vulnerabilities as part of Project Glasswing, a cybersecurity initiative focused on protecting critical infrastructure and open-source software.
Pope Leo has called for stronger global oversight of artificial intelligence, warning that unchecked AI development could fuel misinformation, labor disruption, surveillance, and autonomous warfare.
Anthropic co-founder Chris Olah warned that AI development cannot be left solely to technology companies and called for greater oversight from governments, religious institutions, and civil society.
Anthropic is reportedly preparing to brief the Financial Stability Board on cyber vulnerabilities identified by its Mythos AI model.
OpenAI has renewed calls for an international AI oversight body modeled after the IAEA ahead of the Trump-Xi summit in Beijing. The proposal would place the U.S. at the center of global AI governance while including China in cross-border safety coordination.
Security researchers used Anthropic’s Claude Mythos Preview to help identify vulnerabilities and develop a macOS privilege escalation exploit targeting Apple’s M5 silicon.
Mistral AI is developing a cybersecurity-focused AI model for European banks as institutions seek alternatives to restricted U.S. systems like Anthropic’s Mythos.