Defensive Quantization: When Efficiency Meets Robustness

Understand

Neural network quantization is becoming an industry standard to efficiently deploy deep learning models on hardware platforms, such as CPU, GPU, TPU, and FPGAs.

• However, we observe that the conventional quantization approaches are vulnerable to adversarial attacks.
• This paper aims to raise people's awareness about the security of the quantized models, and we designed a novel quantization methodology to jointly optimize the efficiency and robustness of deep learning models.
• We first conduct an empirical study to show that vanilla quantization suffers more from adversarial attacks.