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: Claude Discovers New Weaknesses in HAWK and Reduced-round AES(39 posts)→
More from Safety
- Scaling AI Safety Grants: Targeted Funds Led by Domain Experts — edelwax · 2026-07-31
- Nature Study: State Media Control Significantly Influences LLM Bias — steverathje2 · 2026-07-31
- Reflections on Hugging Face Agent Incident: Agents Shouldn't Grind for 45 Minutes — HaktanSuren · 2026-07-30
- Study: Flood of AI-Generated Books on Amazon Crowds Out Human Authors — TuhinChakr · 2026-07-30
- Claude Conversations Indexed by Search Engines Sparks SEO and Privacy Debate — btibor91 · 2026-07-30
- AI Age Verification Dilemma: Protect Children or Enable Surveillance? — ShakeelHashim · 2026-07-30