Infrastructure for Verifiable AI: Where Proof Costs Go and How Hardware Can Help
cs.AR, cs.CR, cs.LG
Submitted: 2026-11-12
Updated: 2026-11-12
Code: https://github.com/BLAKE3-team/BLAKE3-specs
Terminology
Sources
- SVIP: Towards Verifiable Inference of Open-source Large Language Models
- TOPLOC: A Locality Sensitive Hashing Scheme for Trustless Verifiable Inference
- Trusting What You Cannot See: Auditable Fine-Tuning and Inference for Proprietary AI
- Verifiable Fine-Tuning for LLMs: Zero-Knowledge Training Proofs Bound to Data Provenance and Policy
- Communication-Efficient Verifiable Attention for LLM Inference
- Verde: Verification via Refereed Delegation for Machine Learning Programs
- A Survey on the Applications of Zero-Knowledge Proofs
- zkLLMPoT: Efficient Zero Knowledge Proof of Training for Large Language Models
- When Proofs Meet Hardware: Comparing NTT and SumCheck in Zero-Knowledge Systems
- Proposals and challenges for zero-knowledge verification of frontier AI training
- ZK-Value: A Practical Zero-Knowledge System for Verifiable Data Valuation
- ZKTorch: Compiling ML Inference to Zero-Knowledge Proofs via Parallel Proof Accumulation
- Jolt Atlas: Verifiable Inference via Lookup Arguments in Zero Knowledge
- Bit-Exact AI Inference Verification Without Performance Tradeoffs
Related papers
- Embedded Arena: Iterative Optimization via Hardware Feedback
- WitCert: Sound Runtime Risk Observability and Gating for KV-Cache Quantization
- SparsePixels: Efficient Convolution for Sparse Data on FPGAs
- Golden Ruler: A Numeric Format Catalog with Bit-Exact Conformance Vectors for FP8, BF16, MXFP4, and Microscaling Formats
- AMMA: A Multi-Chiplet Memory-Centric Architecture for Low-Latency 1M Context Attention Serving
- RFChipAgent: Multi-Agentic AI Flow for Analog/RF Chip Design