paper-with-me

Papers

Evading Adversarial Example Detection Defenses with Orthogonal Projected Gradient Descent

2021-06-28 · ICLR 2022 4 · Oliver Bryniarski, Nabeel Hingun, Pedro Pachuca, Vincent Wang, Nicholas Carlini

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.

📄 PDF Abstract BibTeX arXiv:2106.15023

Code (1)

v-wangg/OrthogonalPGD 공식 구현 pytorch

Similar Papers 제목 키워드 기반

Evading Defenses to Transferable Adversarial Examples by Translation-Invariant Attacks

2019-04-05 · CVPR 2019 6 · Yinpeng Dong, Tianyu Pang, Hang Su, Jun Zhu

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…

Translation

Evading classifiers in discrete domains with provable optimality guarantees

2018-10-25 · Bogdan Kulynych, Jamie Hayes, Nikita Samarin, Carmela Troncoso

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 Detectionvalid

On the Efficacy of Metrics to Describe Adversarial Attacks

2023-01-30 · Tommaso Puccetti, Tommaso Zoppi, Andrea Ceccarelli

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

2021-10-24 · Mingjun Yin, Shasha Li, Chengyu Song, M. Salman Asif 외

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 Detection

Adversarial Machine Learning in Network Intrusion Detection Systems

2020-04-23 · Elie Alhajjar, Paul Maxwell, Nathaniel D. Bastian

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