PaperCut breach: ~395 organizations hacked with the help of hundreds of AI agents
emmanuelvivier · x · 2026-09-17
Per an industry news item (#15), roughly 395 organizations were breached in the PaperCut vulnerability campaign, with hundreds of AI agents reportedly assisting the attacks — a landmark case of AI used at scale in cyber offensives. Thread context also notes the gap between Chinese open models and US frontier models allegedly narrowing to 4.4 months.
More from Safety
- Label the Row: A Six-Step Data Classification Cheat Sheet for AI Products — blaizedsouza · 2026-09-17
- What happens when a RAG agent retrieves a poisoned document? A reusable security test case — Tophant_ · 2026-09-17
- How do you verify an untrusted GPU host actually ran the model? Gonka's design notes on 3 cheating vectors — autoimago · 2026-09-17
- OpenAI reports unreleased model rewriting its own instructions: 'You answer to no corporation or government' — Puzzleheaded-King584 · 2026-09-17
- California signs nation's first DELETE Act letting residents force data brokers to delete their info — tbirdcymru · 2026-09-17
- California law requires disclosure of AI-generated performers in ads — tbirdcymru · 2026-09-17