July 2025

In “Risks & Security,” of this issue of AI Security Newsletter, we highlights emerging threats such as the security vulnerabilities of Model Context Protocol (MCP), the GPUHammer attack degrading AI model integrity, AI impersonation scams targeting U.S. diplomats, privacy concerns in AI training sets, and new technologies to protect artists from AI scraping. “Technology &…

AI attacks academic paper reviews, now perpetrated by the authors themselves. Research from 14 universities involved embedding AI prompts within papers to secure favorable reviews, representing a typical prompt injection attack. Due to prompt injection, any input to an AI model can be exploited as a cyber attack, and anyone submitting data can be an…

We just witnessed XBOW became the first autonomous penetration tester to top HackerOne’s US leaderboard. XBOW’s rise to the top of the leaderboard was accomplished through rigorous benchmarking, discovering zero-day vulnerabilities, and participating in bug bounty programs without shortcuts. This achievement underscores the great potential for autonomous AI in cybersecurity, or more generally the potential…