Non-Negative Networks Against Adversarial Attacks

Understand

Adversarial attacks against neural networks are a problem of considerable importance, for which effective defenses are not yet readily available.

• We make progress toward this problem by showing that non-negative weight constraints can be used to improve resistance in specific scenarios.
• In particular, we show that they can provide an effective defense for binary classification problems with asymmetric cost, such as malware or spam detection.
• We also show the potential for non-negativity to be helpful to non-binary problems by applying it to image classification.