Boosting the Robustness Verification of DNN by Identifying the Achilles's Heel
This work addresses the critical safety issue of verifying DNN robustness for researchers and practitioners, but it is incremental as it builds on existing verification tools like Reluplex.
The paper tackles the problem of time-consuming and unscalable robustness verification for deep neural networks by proposing a boosting method that identifies inputs more likely to have counter-examples, enabling earlier detection. The method was implemented and tested on Reluplex and four attacking methods across two benchmarks, showing effectiveness in experiments.
Deep Neural Network (DNN) is a widely used deep learning technique. How to ensure the safety of DNN-based system is a critical problem for the research and application of DNN. Robustness is an important safety property of DNN. However, existing work of verifying DNN's robustness is time-consuming and hard to scale to large-scale DNNs. In this paper, we propose a boosting method for DNN robustness verification, aiming to find counter-examples earlier. Our observation is DNN's different inputs have different possibilities of existing counter-examples around them, and the input with a small difference between the largest output value and the second largest output value tends to be the achilles's heel of the DNN. We have implemented our method and applied it on Reluplex, a state-of-the-art DNN verification tool, and four DNN attacking methods. The results of the extensive experiments on two benchmarks indicate the effectiveness of our boosting method.