Seal, Then Sample: Sampled Layerwise Proofs for Verifiable LLM Inference from GPT-2 to 70B
cs.CR, cs.IR
Submitted: 2026-09-23
Updated: 2026-09-23
Code: https://github.com/TrueOpen/slpexperiments
Terminology
Sources
- TensorCommitments: A Lightweight Verifiable Inference for Language Models
- IMMACULATE: A Practical LLM Auditing Framework via Verifiable Computation
- TinyLlama: An Open-Source Small Language Model
- AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration
- Pointer Sentinel Mixture Models
- zkComposer: Decomposing Proof Construction to Scale zkML
- zkLLM: Zero Knowledge Proofs for Large Language Models
- Time-Optimal Interactive Proofs for Circuit Evaluation
- Llama 2: Open Foundation and Fine-Tuned Chat Models
- NanoZK: Privacy-Preserving Verifiable Inference for Large Language Models via Layerwise Zero-Knowledge Proofs
- SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models
- TAO: Tolerance-Aware Optimistic Verification for Floating-Point Neural Networks
- A Note on Non-Composability of Layerwise Approximate Verification for Neural Inference
Related papers
- SoK: AI-Augmented Binary Reversing
- Relaxed Sender Anonymity for CBDC Interbank Settlement: A Zero-Knowledge Approach on Permissioned EVM
- Calibration-Family Overfit: Why Trusted Sabotage Monitors Don't Transfer Across Lineages
- Efficient Fuzzy PSI under One-Sided Assumptions
- Sealing the Audit-Runtime Gap for LLM Skills
- Token Composition: A Graph Based on EVM Logs