VeriRouter: Towards Verifiable LLM Routing
cs.CR
Submitted: 2026-10-12
Updated: 2026-10-12
Code: https://github.com/succinctlabs/sp1
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Sources
- Towards Efficient Multi-LLM Inference: Characterization and Analysis of LLM Routing and Hierarchical Techniques
- Are You Getting What You Pay For? Auditing Model Substitution in LLM APIs
- Pr$\epsilon\epsilon$mpt: Sanitizing Sensitive Prompts for LLMs
- IMMACULATE: A Practical LLM Auditing Framework via Verifiable Computation
- RouterBench: A Benchmark for Multi-LLM Routing System
- Your Inference Request Will Become a Black Box: Confidential Inference for Cloud-based Large Language Models
- Trusting What You Cannot See: Auditable Fine-Tuning and Inference for Proprietary AI
- Life-Cycle Routing Vulnerabilities of LLM Router
- Your Agent Is Mine: Measuring Malicious Intermediary Attacks on the LLM Supply Chain
- Automatic and Universal Prompt Injection Attacks against Large Language Models
- Prompt Injection attack against LLM-integrated Applications
- V3DB: Audit-on-Demand Zero-Knowledge Proofs for Verifiable Vector Search over Committed Snapshots
- Attestable Audits: Verifiable AI Safety Benchmarks Using Trusted Execution Environments
- Rerouting LLM Routers
- Evidence-Bound Gateway-Path Provenance for Third-Party LLM Inference
- Privacy-Preserving LLMs Routing
- RerouteGuard: Understanding and Mitigating Adversarial Risks for LLM Routing
- Real Money, Fake Models: Deceptive Model Claims in Shadow APIs
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