Improved Detection of Adversarial Attacks via Penetration Distortion Maximization
This paper is concerned with the defense of deep models against adversarial at- tacks. We develop an adversarial detection method, which is inspired by the cer- tificate defense approach, and captures the idea of separating class clusters in the embedding space so as to increase the margin. The resulting defense is intuitive, effective, scalable and can be integrated into any given neural classification model. Our method demonstrates state-of-the-art detection performance under all threat models.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Reinforcement Learning Platform for Adversarial Black-box Attacks with Custom Distortion Filters
We present a Reinforcement Learning Platform for Adversarial Black-box untargeted and targeted attacks, RLAB, that allows users to select from various distortion filters to create adversarial examples. The platform uses …
image-classificationImage Classificationreinforcement-learningReinforcement LearningEAD: Elastic-Net Attacks to Deep Neural Networks via Adversarial Examples
Recent studies have highlighted the vulnerability of deep neural networks (DNNs) to adversarial examples - a visually indistinguishable adversarial image can easily be crafted to cause a well-trained model to misclassify…
Adversarial AttackAdversarial RobustnessAdversarial Training for Deep Learning-based Intrusion Detection Systems
Nowadays, Deep Neural Networks (DNNs) report state-of-the-art results in many machine learning areas, including intrusion detection. Nevertheless, recent studies in computer vision have shown that DNNs can be vulnerable …
Deep LearningIntrusion DetectionGeneralizable Deepfake Detection with Phase-Based Motion Analysis
We propose PhaseForensics, a DeepFake (DF) video detection method that leverages a phase-based motion representation of facial temporal dynamics. Existing methods relying on temporal inconsistencies for DF detection pres…
Adversarial RobustnessDeepFake DetectionFace SwappingLandmark Tracking+1A Partial Break of the Honeypots Defense to Catch Adversarial Attacks
A recent defense proposes to inject "honeypots" into neural networks in order to detect adversarial attacks. We break the baseline version of this defense by reducing the detection true positive rate to 0\% and the detec…