ReplayAudit: Auditing Outsourced LLM Fine-Tuning via Sealed Records and Selective Replay
cs.CR, cs.LG
Submitted: 2026-11-06
Updated: 2026-11-06
Terminology
Sources
- Verifiable Fine-Tuning for LLMs: Zero-Knowledge Training Proofs Bound to Data Provenance and Policy
- Verde: Verification via Refereed Delegation for Machine Learning Programs
- OPEN-1B: A Fully Auditable Training Run
- The Llama 3 Herd of Models
- Trusting What You Cannot See: Auditable Fine-Tuning and Inference for Proprietary AI
- zkLLMPoT: Efficient Zero Knowledge Proof of Training for Large Language Models
- VeriLoRA: Fine-Tuning Large Language Models with Verifiable Security via Zero-Knowledge Proofs
- Seal, Then Sample: Sampled Layerwise Proofs for Verifiable LLM Inference from GPT-2 to 70B
- Qwen2.5 Technical Report
- Optimistic Verifiable Training by Controlling Hardware Nondeterminism
- NanoZK: Privacy-Preserving Verifiable Inference for Large Language Models via Layerwise Zero-Knowledge Proofs
Related papers
- From Strategy Search to Policy Learning: MCTS-Guided Adversarial Co-Evolution for LLM Safety Alignment
- Privacy Leakage from Recurrent State in LLM Inference
- Incrementally Verifiable Oracle Aided Computation
- Privilege and confidentiality in generative AI workflows
- BadMoE: Backdooring Mixture-of-Experts LLMs via Routing-Aware Triggers and Task-Underutilized Experts
- CoVault: Secure, Scalable Analytics of Personal Data