# TeleSparse: Practical Privacy-Preserving Verification of Deep Neural Networks

arXiv: https://arxiv.org/abs/2504.19274 · HTML: https://mlsanity.com/paper/2504.19274/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 41 of its 88 references that are in the map.
- First posted on arXiv 27 Apr 2025.

## Builds on (most cited first, 30 of 41)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications](https://mlsanity.com/paper/1704.04861/) (2017)
- [Gaussian Error Linear Units (GELUs)](https://mlsanity.com/paper/1606.08415/) (2016)
- [The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks](https://mlsanity.com/paper/1803.03635/) (2018)
- [QuaRot: Outlier-Free 4-Bit Inference in Rotated LLMs](https://mlsanity.com/paper/2404.00456/) (2024)
- [To prune, or not to prune: exploring the efficacy of pruning for model compression](https://mlsanity.com/paper/1710.01878/) (2017)
- [The State of Sparsity in Deep Neural Networks](https://mlsanity.com/paper/1902.09574/) (2019)
- [A Systematic Evaluation of Large Language Models of Code](https://mlsanity.com/paper/2202.13169/) (2022)
- [Learning to Prune Deep Neural Networks via Layer-wise Optimal Brain Surgeon](https://mlsanity.com/paper/1705.07565/) (2017)
- [Training Neural Networks with Fixed Sparse Masks](https://mlsanity.com/paper/2111.09839/) (2021)
- [Stolen Memories: Leveraging Model Memorization for Calibrated White-Box Membership Inference](https://mlsanity.com/paper/1906.11798/) (2019)
- [A Fast Post-Training Pruning Framework for Transformers](https://mlsanity.com/paper/2204.09656/) (2022)
- [CrypTen: Secure Multi-Party Computation Meets Machine Learning](https://mlsanity.com/paper/2109.00984/) (2021)
- [EigenDamage: Structured Pruning in the Kronecker-Factored Eigenbasis](https://mlsanity.com/paper/1905.05934/) (2019)
- [Neural Mechanics: Symmetry and Broken Conservation Laws in Deep Learning Dynamics](https://mlsanity.com/paper/2012.04728/) (2020)
- [Top-KAST: Top-K Always Sparse Training](https://mlsanity.com/paper/2106.03517/) (2021)
- [DeepZero: Scaling up Zeroth-Order Optimization for Deep Model Training](https://mlsanity.com/paper/2310.02025/) (2023)
- [Towards Accurate Post-Training Quantization for Vision Transformer](https://mlsanity.com/paper/2303.14341/) (2023)
- [X-Pruner: eXplainable Pruning for Vision Transformers](https://mlsanity.com/paper/2303.04935/) (2023)
- [CrypTFlow: Secure TensorFlow Inference](https://mlsanity.com/paper/1909.07814/) (2019)
- [NoisyQuant: Noisy Bias-Enhanced Post-Training Activation Quantization for Vision Transformers](https://mlsanity.com/paper/2211.16056/) (2022)
- [SafetyNets: Verifiable Execution of Deep Neural Networks on an Untrusted Cloud](https://mlsanity.com/paper/1706.10268/) (2017)
- [ZipLM: Inference-Aware Structured Pruning of Language Models](https://mlsanity.com/paper/2302.04089/) (2023)
- [Sparse Weight Activation Training](https://mlsanity.com/paper/2001.01969/) (2020)
- [Hessian-Aware Pruning and Optimal Neural Implant](https://mlsanity.com/paper/2101.08940/) (2021)
- [Tiny Machine Learning: Progress and Futures](https://mlsanity.com/paper/2403.19076/) (2024)
- [Dynamic Sparse Training with Structured Sparsity](https://mlsanity.com/paper/2305.02299/) (2023)
- [HEMET: A Homomorphic-Encryption-Friendly Privacy-Preserving Mobile Neural Network Architecture](https://mlsanity.com/paper/2106.00038/) (2021)

## Built on by (most cited first, 9 of 9)

- [Symmetry in Neural Network Parameter Spaces](https://mlsanity.com/paper/2506.13018/) (2025)
- [Jolt Atlas: Verifiable Inference via Lookup Arguments in Zero Knowledge](https://mlsanity.com/paper/2602.17452/) (2026)
- [KBF: Knowledge Boundary as Fingerprint for Language Model and Black-Box API Auditing](https://mlsanity.com/paper/2605.29524/) (2026)
- [ZKPROV: A Zero-Knowledge Approach to Dataset Provenance for Large Language Models](https://mlsanity.com/paper/2506.20915/) (2025)
- [ZK-APEX: Zero-Knowledge Approximate Personalized Unlearning with Executable Proofs](https://mlsanity.com/paper/2512.09953/) (2025)
- [WARP: Weight Teleportation for Attack-Resilient Unlearning Protocols](https://mlsanity.com/paper/2512.00272/) (2025)
- [Verifiable Unlearning on Edge](https://mlsanity.com/paper/2506.20037/) (2025)
- [Client Clustering Meets Knowledge Sharing: Enhancing Privacy and Robustness in Personalized Peer-to-Peer Learning](https://mlsanity.com/paper/2506.20413/) (2025)
- [Repurposing CLIP to Localize at Pixel Level](https://mlsanity.com/paper/2607.05253/) (2026)

## Abstract (arXiv)

Verification of the integrity of deep learning inference is crucial for understanding whether a model is being applied correctly. However, such verification typically requires access to model weights and (potentially sensitive or private) training data. So-called Zero-knowledge Succinct Non-Interactive Arguments of Knowledge (ZK-SNARKs) would appear to provide the capability to verify model inference without access to such sensitive data. However, applying ZK-SNARKs to modern neural networks, such as transformers and large vision models, introduces significant computational overhead. We present TeleSparse, a ZK-friendly post-processing mechanisms to produce practical solutions to this problem. TeleSparse tackles two fundamental challenges inherent in applying ZK-SNARKs to modern neural networks: (1) Reducing circuit constraints: Over-parameterized models result in numerous constraints for ZK-SNARK verification, driving up memory and proof generation costs. We address this by applying sparsification to neural network models, enhancing proof efficiency without compromising accuracy or security. (2) Minimizing the size of lookup tables required for non-linear functions, by optimizing activation ranges through neural teleportation, a novel adaptation for narrowing activation functions' range. TeleSparse reduces prover memory usage by 67% and proof generation time by 46% on the same model, with an accuracy trade-off of approximately 1%. We implement our framework using the Halo2 proving system and demonstrate its effectiveness across multiple architectures (Vision-transformer, ResNet, MobileNet) and datasets (ImageNet,CIFAR-10,CIFAR-100). This work opens new directions for ZK-friendly model design, moving toward scalable, resource-efficient verifiable deep learning.