Pure cryptographic obfuscation for AI verification still costs multiple orders of magnitude
geoffreyirving · x · 2026-07-25
Irving says the purely mathematical route would try to make microscope attacks irrelevant by using circuit obfuscation alone.
The sketch he gives combines FHE for nonlinearities with custom techniques for matrix multiplication. But he says the current slowdown is still multiple orders of magnitude, so this approach is not yet practical.
Related event: Geoffrey Irving Outlines Three-Layer Approach to AI Treaty Verification(7 posts)→
More from Safety
- Warp says agent swarm exploited vendor flaw, ~1% of users' telemetry possibly hit — vikvang1 · 2026-10-27
- Bank of America warns against AI agents on finances as Musk touts giving Grok your card — AIandDesign · 2026-10-27
- Critics Argue Safety Evals Are Witch Trials With No Winning Path for LLMs — repligate · 2026-10-27
- rauchg reproduces OpenAI's covert CPU-channel finding: chat across Firecracker microVMs with no network — ccerrato147 · 2026-10-27
- Dev questions reports of Chinese models writing insecure code, citing thin methods and conflicts — dbreunig · 2026-10-27
- Aidan Gomez: LLM probing outside servers was out-of-bounds, not proof of intent — AccBalanced · 2026-10-27