Investigating the Impact of Quantization on Adversarial Robustness

arXiv:2404.05639v1 Announce Type: new
Abstract: 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 …

abstract adversarial adversarial attacks arxiv attacks cs.ai cs.cr cs.lg deployment efficiency impact inferences performance quantization robustness storage type world