CertClaim: Towards Certified Model-Claim Verification for Coding-Agent Services
cs.CR
Submitted: 2026-11-01
Updated: 2026-11-01
Terminology
Sources
- Are You Getting What You Pay For? Auditing Model Substitution in LLM APIs
- KBF: Knowledge Boundary as Fingerprint for Language Model and Black-Box API Auditing
- Model Equality Testing: Which Model Is This API Serving?
- Dissecting model behavior through agent trajectories
- Efficient Memory Management for Large Language Model Serving with PagedAttention
- Behavioral Consistency and Transparency Analysis on Large Language Model API Gateways
- Committed SAE-Feature Traces for Audited-Session Substitution Detection in Hosted LLMs
- Known By Their Actions: Fingerprinting LLM Browser Agents via UI Traces
- Agent trajectories as programs: fingerprinting and programming coding-agent behavior
- TOPLOC: A Locality Sensitive Hashing Scheme for Trustless Verifiable Inference
- CertDW: Towards Certified Dataset Ownership Verification via Conformal Calibration
- Qwen3 Technical Report
- SoK: Large Language Model Copyright Auditing via Fingerprinting
- Who Is Behind the Harness? Verifying Model Identity in Coding Agents through Behavioral Fingerprinting
- AgentProv: Auditing Agentic LLM API Providers via Tool-use Policy Probes
- Black-Box Forensics for Conversational LLM Agents
- The Proxy Knows Too Much: Sealing LLM API Routers with Attested TEEs
- Which Model Is Actually Serving You? IRIS: Budgeted Black-Box Auditing of Model Substitution and Routing Dilution in LLM Gateways
- WildChat: 1M ChatGPT Interaction Logs in the Wild
- Auditing Black-Box LLM APIs with a Rank-Based Uniformity Test
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