# Detection and Recovery Against Deep Neural Network Fault Injection Attacks Based on Contrastive Learning

arXiv: https://arxiv.org/abs/2401.16766 · HTML: https://mlsanity.com/paper/2401.16766/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 5 of its 13 references that are in the map.
- First posted on arXiv 30 Jan 2024.

## Builds on (most cited first, 5 of 5)

- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Intriguing properties of neural networks](https://mlsanity.com/paper/1312.6199/) (2013)
- [Bit-Flip Attack: Crushing Neural Network with Progressive Bit Search](https://mlsanity.com/paper/1903.12269/) (2019)
- [Structured Adversarial Attack: Towards General Implementation and Better Interpretability](https://mlsanity.com/paper/1808.01664/) (2018)
- [Fault Sneaking Attack: a Stealthy Framework for Misleading Deep Neural Networks](https://mlsanity.com/paper/1905.12032/) (2019)

## Abstract (arXiv)

Deep Neural Network (DNN) models when implemented on executing devices as the inference engines are susceptible to Fault Injection Attacks (FIAs) that manipulate model parameters to disrupt inference execution with disastrous performance. This work introduces Contrastive Learning (CL) of visual representations i.e., a self-supervised learning approach into the deep learning training and inference pipeline to implement DNN inference engines with self-resilience under FIAs. Our proposed CL based FIA Detection and Recovery (CFDR) framework features (i) real-time detection with only a single batch of testing data and (ii) fast recovery effective even with only a small amount of unlabeled testing data. Evaluated with the CIFAR-10 dataset on multiple types of FIAs, our CFDR shows promising detection and recovery effectiveness.