Evading Adversarial Example Detection Defenses with Orthogonal Projected Gradient Descent
Evading adversarial example detection defenses requires finding adversarial examples that must simultaneously (a) be misclassified by the model and (b) be detected as non-adversarial. We find that existing attacks that attempt to satisfy multiple simultaneous constraints often over-optimize against one constraint at the cost of satisfying another. We introduce Orthogonal Projected Gradient Descent, an improved attack technique to generate adversarial examples that avoids this problem by orthogonalizing the gradients when running standard gradient-based attacks. We use our technique to evade four state-of-the-art detection defenses, reducing their accuracy to 0% while maintaining a 0% detection rate.
Code (1)
Similar Papers 제목 키워드 기반
Evading Defenses to Transferable Adversarial Examples by Translation-Invariant Attacks
Deep neural networks are vulnerable to adversarial examples, which can mislead classifiers by adding imperceptible perturbations. An intriguing property of adversarial examples is their good transferability, making black…
TranslationEvading classifiers in discrete domains with provable optimality guarantees
Machine-learning models for security-critical applications such as bot, malware, or spam detection, operate in constrained discrete domains. These applications would benefit from having provable guarantees against advers…
Adversarial RobustnessSpam detectionTwitter Bot DetectionvalidOn the Efficacy of Metrics to Describe Adversarial Attacks
Adversarial defenses are naturally evaluated on their ability to tolerate adversarial attacks. To test defenses, diverse adversarial attacks are crafted, that are usually described in terms of their evading capability an…
ADC: Adversarial attacks against object Detection that evade Context consistency checks
Deep Neural Networks (DNNs) have been shown to be vulnerable to adversarial examples, which are slightly perturbed input images which lead DNNs to make wrong predictions. To protect from such examples, various defense st…
Objectobject-detectionObject DetectionAdversarial Machine Learning in Network Intrusion Detection Systems
Adversarial examples are inputs to a machine learning system intentionally crafted by an attacker to fool the model into producing an incorrect output. These examples have achieved a great deal of success in several doma…
BIG-bench Machine LearningIntrusion DetectionNetwork Intrusion DetectionSpam detection+2