Quantization-aware Interval Bound Propagation for Training Certifiably Robust Quantized Neural Networks
This work addresses the critical need for robust and efficient neural networks in industry applications, where quantization is common but can compromise security, though it is incremental as it builds on prior robust learning techniques.
The paper tackles the problem of training and certifying adversarially robust quantized neural networks (QNNs), which are vulnerable to attacks after quantization, by introducing quantization-aware interval bound propagation (QA-IBP) and a GPU-accelerated verification procedure, achieving state-of-the-art results with significant performance improvements over existing methods.
We study the problem of training and certifying adversarially robust quantized neural networks (QNNs). Quantization is a technique for making neural networks more efficient by running them using low-bit integer arithmetic and is therefore commonly adopted in industry. Recent work has shown that floating-point neural networks that have been verified to be robust can become vulnerable to adversarial attacks after quantization, and certification of the quantized representation is necessary to guarantee robustness. In this work, we present quantization-aware interval bound propagation (QA-IBP), a novel method for training robust QNNs. Inspired by advances in robust learning of non-quantized networks, our training algorithm computes the gradient of an abstract representation of the actual network. Unlike existing approaches, our method can handle the discrete semantics of QNNs. Based on QA-IBP, we also develop a complete verification procedure for verifying the adversarial robustness of QNNs, which is guaranteed to terminate and produce a correct answer. Compared to existing approaches, the key advantage of our verification procedure is that it runs entirely on GPU or other accelerator devices. We demonstrate experimentally that our approach significantly outperforms existing methods and establish the new state-of-the-art for training and certifying the robustness of QNNs.