论文标题
改善体重量化神经网络中的对抗性鲁棒性
Improving Adversarial Robustness in Weight-quantized Neural Networks
论文作者
论文摘要
如今，神经网络越来越深，计算密集型。量化是在硬件平台上部署神经网络并以可忽略的性能损失来节省计算成本的一种有用技术。但是，最近的研究表明，无论是完全精确或量化的神经网络模型，都容易受到对抗性攻击的影响。在这项工作中，我们分析了对抗性和量化损失，然后引入标准以评估它们。我们提出了一种基于边界的再培训方法，以减轻对抗性和量化损失，并采用非线性映射方法来防御基于白盒梯度的对抗攻击。评估表明，在量化后，我们的方法比黑框和白框对抗攻击的其他基线方法更好地恢复了准确性。结果还表明，对抗训练会遭受量化损失，并且与其他培训方法不太合作。
Neural networks are getting deeper and more computation-intensive nowadays. Quantization is a useful technique in deploying neural networks on hardware platforms and saving computation costs with negligible performance loss. However, recent research reveals that neural network models, no matter full-precision or quantized, are vulnerable to adversarial attacks. In this work, we analyze both adversarial and quantization losses and then introduce criteria to evaluate them. We propose a boundary-based retraining method to mitigate adversarial and quantization losses together and adopt a nonlinear mapping method to defend against white-box gradient-based adversarial attacks. The evaluations demonstrate that our method can better restore accuracy after quantization than other baseline methods on both black-box and white-box adversarial attacks. The results also show that adversarial training suffers quantization loss and does not cooperate well with other training methods.
