Tabula: Efficiently Computing Nonlinear Activation Functions for Secure Neural Network Inference

Lam, Maximilian; Mitzenmacher, Michael; Reddi, Vijay Janapa; Wei, Gu-Yeon; Brooks, David J.

doi:10.48550/arxiv.2203.02833

Cited by 2 publications

(3 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In general, activation functions that are non-linear can be very effectively implemented in quantization runtime Lam et al (2022). However these considerations are hardware agnostic.…”

Section: K Overhead Cost Discussionmentioning

confidence: 99%

PowerQuant: Automorphism Search for Non-Uniform Quantization

Yvinec¹,

Dapogny²,

Cord³

et al. 2023

Preprint

View full text Add to dashboard Cite

Deep neural networks (DNNs) are nowadays ubiquitous in many domains such as computer vision. However, due to their high latency, the deployment of DNNs hinges on the development of compression techniques such as quantization which consists in lowering the number of bits used to encode the weights and activations. Growing concerns for privacy and security have motivated the development of data-free techniques, at the expanse of accuracy. In this paper, we identity the uniformity of the quantization operator as a limitation of existing approaches, and propose a data-free non-uniform method. More specifically, we argue that to be readily usable without dedicated hardware and implementation, non-uniform quantization shall not change the nature of the mathematical operations performed by the DNN. This leads to search among the continuous automorphisms of (R * + , ×), which boils down to the power functions defined by their exponent. To find this parameter, we propose to optimize the reconstruction error of each layer: in particular, we show that this procedure is locally convex and admits a unique solution. At inference time, we show that our approach, dubbed PowerQuant, only require simple modifications in the quantized DNN activation functions. As such, with only negligible overhead, it significantly outperforms existing methods in a variety of configurations.

show abstract

“…In general, activation functions that are non-linear can be very effectively implemented in quantization runtime Lam et al (2022). However these considerations are hardware agnostic.…”

Section: K Overhead Cost Discussionmentioning

confidence: 99%

PowerQuant: Automorphism Search for Non-Uniform Quantization

Yvinec¹,

Dapogny²,

Cord³

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…The most common methods of doing secure ML are with multi-party computation (MPC), homomorphic encryption (HE), or interactive proofs (IPs). As we describe, these methods are either impractical, do not work in the face of malicious adversaries (Knott et al, 2021;Kumar et al, 2020;Lam et al, 2022;Mishra et al, 2020), or do not hide the weights/inputs (Ghodsi et al, 2017b). In this work, we propose practical methods of doing verified ML execution in the face of malicious adversaries.…”

Section: Related Workmentioning

confidence: 99%

“…MPC. One of the most common methods of doing secure ML is with MPCs, in which the computation is shared across multiple parties (Knott et al, 2021;Kumar et al, 2020;Lam et al, 2022;Mishra et al, 2020;Jha et al, 2021). There are a variety of MPC protocols with different guarantees.…”

Section: Related Workmentioning

confidence: 99%

Scaling up Trustless DNN Inference with Zero-Knowledge Proofs

Kang¹,

Hashimoto²,

Stoica³

et al. 2022

Preprint

View full text Add to dashboard Cite

As ML models have increased in capabilities and accuracy, so has the complexity of their deployments. Increasingly, ML model consumers are turning to service providers to serve the ML models in the ML-as-a-service (MLaaS) paradigm. As MLaaS proliferates, a critical requirement emerges: how can model consumers verify that the correct predictions were served, in the face of malicious, lazy, or buggy service providers?In this work, we present the first ImageNetscale method to verify ML model execution noninteractively. To do so, we leverage recent developments in ZK-SNARKs (zero-knowledge succinct non-interactive argument of knowledge), a form of zero-knowledge proofs. ZK-SNARKs allows us to verify ML model execution noninteractively and with only standard cryptographic hardness assumptions. In particular, we provide the first ZK-SNARK proof of valid inference for a full resolution ImageNet model, achieving 79% top-5 accuracy. We further use these ZK-SNARKs to design protocols to verify ML model execution in a variety of scenarios, including for verifying MLaaS predictions, verifying MLaaS model accuracy, and using ML models for trustless retrieval. Together, our results show that ZK-SNARKs have the promise to make verified ML model inference practical.

show abstract

Tabula: Efficiently Computing Nonlinear Activation Functions for Secure Neural Network Inference

Cited by 2 publications

References 13 publications

PowerQuant: Automorphism Search for Non-Uniform Quantization

PowerQuant: Automorphism Search for Non-Uniform Quantization

Scaling up Trustless DNN Inference with Zero-Knowledge Proofs

Contact Info

Product

Resources

About