Study: Terrorist Groups Use Mainstream AI Chatbots for Attack Planning
The Decoder · rss · 2026-07-12
A Cambridge University study found that terrorist groups like Boko Haram are using mainstream AI chatbots such as ChatGPT, Claude, and Gemini to plan attacks, manufacture explosives, and maintain weapons. Since 2023, ISIS militants have been training the group's commanders on how to bypass AI system safety filters.
The study notes that existing safety filters have repeatedly failed to prevent such misuse, indicating that voluntary self-regulation by AI providers is clearly insufficient to address security threats.
More from Safety
- A 13KB Markdown file can hijack Claude Code and Codex via your Downloads folder — pbaylies · 2026-10-26
- If an agent can rewrite itself, does your consent still mean anything? — tallmetommy · 2026-10-26
- 109 of 529 AI Agent Incidents Involved No Adversary, Arguing Red Teams Must Test Normal Operation — anacondainc · 2026-10-26
- Cryptographer Matthew Green: if your code looks vulnerable, fix it now — matthew_d_green · 2026-10-26
- Filtering secrets on the write path: why agent memory deserves more suspicion at ingest than retrieval — Classic-Being-7960 · 2026-10-26
- After OpenCode key leak: 5 practical rules for keeping keys away from agents — jacobholm_dev · 2026-10-26