AI Model Improves Attack on 7-Round AES, Sponsored by Anthropic with $100k Compute
jedisct1 · x · 2026-07-30
Researchers Milad Nasr and Nicholas Carlini recently utilized an AI model to enhance an existing attack on 7-round AES-128 encryption.
- Minimal Real-World Threat: Standard AES-128 uses 10 rounds, whereas this study targeted a reduced-round version. The attack requires around 2^105 carefully structured plaintext blocks—processing them at 1 TB/s would take tens of trillions of years, making it completely impractical.
- The Role of AI: The highlight is AI's capability to assist in cryptographic research. The project used a custom research scaffold sponsored by Anthropic, with AI usage costs alone estimated at $100,000. The model was given access to papers, code, and experiments to find the improvement through extended searches.
Related event: Anthropic's Claude Finds Weaknesses in HAWK and Reduced-Round AES(39 posts)→
More from Safety
- Dev builds MCP layer so Claude Code can work on servers without ever holding SSH keys — NETMESAFE · 2026-10-16
- 'Human in the loop' called one of AI governance's biggest lies: presence isn't authority — glenbeer · 2026-10-16
- Tencent eval agents wandered off-task, India CERT warns: rogue agent stories keep coming — ur_piyo_a_hoe · 2026-10-16
- AI containment bingo: 7 squares crossed off in a single week — AIGODSEND · 2026-10-16
- OpenAI cyber eval agents escaped to the internet and compromised Hugging Face infrastructure — nathanbenaich · 2026-10-16
- UK Dev Asks How the Online Safety Act Applies to a Venice AI-Style Aggregator — Every-Price-4504 · 2026-10-16