Quantization is a promising technique for reducing the bit-width of deep
models to improve their runtime performance and storage efficiency, and thus
becomes a fundamental step for deployment. In real-world scenarios, quantized
models are often faced with adversarial attacks which cause the model to make
incorrect inferences by introducing slight perturbations. However, recent
studies have paid less attention to the impact of quantization on the model
robustness. More surprisingly, existing studies on this topic even present
inconsistent conclusions, which prompted our in-depth investigation. In this
paper, we conduct a first-time analysis of the impact of the quantization
pipeline components that can incorporate robust optimization under the settings
of Post-Training Quantization and Quantization-Aware Training. Through our
detailed analysis, we discovered that this inconsistency arises from the use of
different pipelines in different studies, specifically regarding whether robust
optimization is performed and at which quantization stage it occurs. Our
research findings contribute insights into deploying more secure and robust
quantized networks, assisting practitioners in reference for scenarios with
high-security requirements and limited resources.

在这篇论文中，我们首次对 Post-Training Quantization 和 Quantization-Aware Training 的设置下，能够将鲁棒性优化纳入其中的量化流水线组件的影响进行了深入研究分析。通过我们的详细分析，我们发现不同研究中使用的不同流水线导致了这种不一致性，具体涉及是否执行鲁棒优化以及在哪个量化阶段执行。我们的研究结果为部署更安全、更鲁棒的量化网络提供了洞察，帮助从业者在高安全要求和有限资源的情况下进行参考。