Sources
On this page
- AH. Sun et al. (2024). zkLLM: Zero Knowledge Proofs for Large Language Models. 2024 ACM SIGSAC Conference on Computer and Communications Security (CCS 2024). Source recordSupports: design, threat model, security theorems, overheads, accuracy, comparison with zkML · abstract; §3.6; §4; §5; §7; §8 Table 1 and Fig. 4; §9
- BH. Sun (2024). zkllm-ccs2024: code for zkLLM: Zero Knowledge Proofs for Large Language Models. GitHub; archived on Zenodo. Source recordSupports: public code, artifact badges, supported models, README caveats, archive status · README; Zenodo record 13621754
- BN. Cankaya (2026). A System Overview for Near-Term, Low-Trust AI Compute Verification. Machine Intelligence Research Institute. Source recordSupports: use of zkLLM's figures in a verification system design · §5.2.4
- BC. Gong et al. (2026). Hollow-LLM Attack: Computationally Trivial Weights in Zero-Knowledge Verification of LLM Inference. arXiv. Source recordSupports: independent Hollow-LLM analysis: valid proofs in zkLLM-style deployments do not bind computational effort; demonstrated with zkGPT · Abstract; threat model; §V