Backlog
Backlog
Indexed but not yet read. Honest about what we have not done.
Known of, not read
These have no entry in the corpus proper — no benchmark numbers, no provenance, no page. They are listed so that the size of what we have not done stays visible.
| Paper | Date | Category | Note |
|---|---|---|---|
| Verifiable Fine-Tuning for LLMs: Zero-Knowledge Training Proofs Bound to Data Provenance and Policy | 2025-10 | training | |
| VeriLLM: A Lightweight Framework for Publicly Verifiable Decentralized Inference | 2025-09 | inference | |
| ZKProphet: Understanding Performance of Zero-Knowledge Proofs on GPUs | 2025-09 | infrastructure | |
| Range-Arithmetic: Verifiable Deep Learning Inference on an Untrusted Party | 2025-05 | inference | Turns rounding-after-matmul and ReLU into arithmetic steps verifiable by sum-check + concatenated range proofs; avoids Boolean encoding and large lookup tables. Real zkML inference optimization, fully sound -- not a sampling scheme. |
| Engineering Trustworthy Machine-Learning Operations with Zero-Knowledge Proofs | 2025-05 | infrastructure | |
| Bionetta: Efficient Client-Side Zero-Knowledge Machine Learning Proving | 2025 | inference | Cited by both DeepProve [ea25a] and Jolt Atlas. Groth16/UltraGroth, client-side, EVM on-chain verification; weights hardcoded into the circuit (0-constraint fixed-matrix mul). General ML, NOT LLM-specific, no general ONNX support. Not a graph candidate; track for completeness. |
| Zhan et al. | 2024-11 | inference | |
| Lookup arguments for decision trees (cq+, zkcq+, cq++) | 2024-04 | testing | |
| South et al. | 2024-02 | inference | |
| MSCProof | 2023-10 | inference | |
| Fan et al. | 2023-05 | inference | |
| ezDPS | 2022-12 | inference | Zero-knowledge data processing pipeline (not just the model). |
| Kang et al. (Scaling up Trustless DNN Inference) | 2022-10 | inference | |
| Singh et al. (decision trees) | 2022-10 | inference | 170-200s proving, 0.4s verify. |
| Hydra | 2021-12 | inference | |
| Hydra | 2021-12 | training | Interactive quantization algorithm: rounds+freezes bottom layers, then quantizes upward. Listed twice -- survey puts it under training. |
| Drynx | 2020-03 | inference | Regression over 600k records: <22s proving, 56kB proof. |
| Verifiable evaluations of machine learning models using zkSNARKs | — | testing | |
| Efficient Public Verification of Private ML via Regularization | — | inference | |
| zk-OPML | — | inference | Hybrid optimistic verification + ZKP for isolated ONNX operators. |
| awesome-zkml (link collection) | — | infrastructure | |
| Zero-Knowledge AI Inference with High Precision | — | inference | Cited by DeepProve [RWB+25]. HIGHEST-PRIORITY follow-up: recent, peer-reviewed, and its 'high precision' angle is the exact accuracy/floating-point axis DeepProve and zkLLM contest. Unknown whether it targets LLMs or general ML -- needs to be pulled and read. |
| An Efficient and Extensible Zero-knowledge Proof Framework for Neural Networks | — | inference | Cited by DeepProve. Same core authors as zkGPT (Wenjie Qu, Jiaheng Zhang) -- likely zkGPT's general-NN sibling or precursor. Check whether it is distinct from zkGPT before adding as a separate system. |