# DeepDyve: Dynamic Verification for Deep Neural Networks

arXiv: https://arxiv.org/abs/2009.09663 · HTML: https://mlsanity.com/paper/2009.09663/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Sep 2020.

## Built on by (most cited first, 12 of 12)

- ["Real Attackers Don't Compute Gradients": Bridging the Gap Between Adversarial ML Research and Practice](https://mlsanity.com/paper/2212.14315/) (2022)
- [Quantization Backdoors to Deep Learning Commercial Frameworks](https://mlsanity.com/paper/2108.09187/) (2021)
- [RA-BNN: Constructing Robust & Accurate Binary Neural Network to Simultaneously Defend Adversarial Bit-Flip Attack and Improve Accuracy](https://mlsanity.com/paper/2103.13813/) (2021)
- [Arithmetic-Intensity-Guided Fault Tolerance for Neural Network Inference on GPUs](https://mlsanity.com/paper/2104.09455/) (2021)
- [HASHTAG: Hash Signatures for Online Detection of Fault-Injection Attacks on Deep Neural Networks](https://mlsanity.com/paper/2111.01932/) (2021)
- [Machine Learning for Intrusion Detection in Industrial Control Systems: Applications, Challenges, and Recommendations](https://mlsanity.com/paper/2202.11917/) (2022)
- [Don't Knock! Rowhammer at the Backdoor of DNN Models](https://mlsanity.com/paper/2110.07683/) (2021)
- [NTD: Non-Transferability Enabled Backdoor Detection](https://mlsanity.com/paper/2111.11157/) (2021)
- [Verifiable Obstacle Detection](https://mlsanity.com/paper/2208.14403/) (2022)
- [Compiled Models, Built-In Exploits: Uncovering Pervasive Bit-Flip Attack Surfaces in DNN Executables](https://mlsanity.com/paper/2309.06223/) (2023)
- [The Weight of a Bit: EMFI Sensitivity Analysis of Embedded Deep Learning Models](https://mlsanity.com/paper/2602.16309/) (2026)
- [MAED: Mathematical Activation Error Detection for Mitigating Physical Fault Attacks in DNN Inference](https://mlsanity.com/paper/2603.18120/) (2026)

## Abstract (arXiv)

Deep neural networks (DNNs) have become one of the enabling technologies in many safety-critical applications, e.g., autonomous driving and medical image analysis. DNN systems, however, suffer from various kinds of threats, such as adversarial example attacks and fault injection attacks. While there are many defense methods proposed against maliciously crafted inputs, solutions against faults presented in the DNN system itself (e.g., parameters and calculations) are far less explored. In this paper, we develop a novel lightweight fault-tolerant solution for DNN-based systems, namely DeepDyve, which employs pre-trained neural networks that are far simpler and smaller than the original DNN for dynamic verification. The key to enabling such lightweight checking is that the smaller neural network only needs to produce approximate results for the initial task without sacrificing fault coverage much. We develop efficient and effective architecture and task exploration techniques to achieve optimized risk/overhead trade-off in DeepDyve. Experimental results show that DeepDyve can reduce 90% of the risks at around 10% overhead.