Towards Robust Detection of Adversarial Examples

Understand

Although the recent progress is substantial, deep learning methods can be vulnerable to the maliciously generated adversarial examples.

• In this paper, we present a novel training procedure and a thresholding test strategy, towards robust detection of adversarial examples.
• In training, we propose to minimize the reverse cross-entropy (RCE), which encourages a deep network to learn latent representations that better distinguish adversarial examples from normal ones.
• In testing, we propose to use a thresholding strategy as the detector to filter out adversarial examples for reliable predictions.