CuraSec

tag: Zero-Knowledge · 1 items

Learn archived Hollow-LLM Attack Breaks ZK Proof Binding in LLM Inference
2026-08-03 · arXiv cs.CR · source ↗ #ai-security#cryptography#zero-knowledge
  • Engineer — Learn: Novel research showing ZK verification of LLM inference can be satisfied by ghost weights that collapse effective computation, letting a provider overclaim model size while proofs remain valid. Engineers building or relying on ZK-ML attestation for supply-chain trust should revisit those assumptions before treating ZK proofs as effort guarantees.
  • SOC/IR — Skip
  • Leader — Skip