Towards Feature Space Adversarial Attack
We propose a new adversarial attack to Deep Neural Networks for image classification. Different from most existing attacks that directly perturb input pixels, our attack focuses on perturbing abstract features, more specifically, features that denote styles, including interpretable styles such as vivid colors and sharp outlines, and uninterpretable ones. It induces model misclassfication by injecting imperceptible style changes through an optimization procedure. We show that our attack can generate adversarial samples that are more natural-looking than the state-of-the-art unbounded attacks. The experiment also supports that existing pixel-space adversarial attack detection and defense techniques can hardly ensure robustness in the style related feature space.
Code (1)
Tasks
Adversarial AttackAdversarial Attack Detectionimage-classificationImage ClassificationSimilar Papers 제목 키워드 기반
DifAttack: Query-Efficient Black-Box Attack via Disentangled Feature Space
This work investigates efficient score-based black-box adversarial attacks with a high Attack Success Rate (ASR) and good generalizability. We design a novel attack method based on a Disentangled Feature space, called Di…
DisentanglementDifAttack++: Query-Efficient Black-Box Adversarial Attack via Hierarchical Disentangled Feature Space in Cross-Domain
This work investigates efficient score-based black-box adversarial attacks with a high Attack Success Rate (\textbf{ASR}) and good generalizability. We design a novel attack method based on a hierarchical DIsentangled Fe…
Adversarial AttackDisentanglementDefending against Adversarial Malware Attacks on ML-based Android Malware Detection Systems
Android malware presents a persistent threat to users' privacy and data integrity. To combat this, researchers have proposed machine learning-based (ML-based) Android malware detection (AMD) systems. However, adversarial…
Adversarial RobustnessAndroid Malware DetectionMalware DetectionA Hierarchical Feature Constraint to Camouflage Medical Adversarial Attacks
Deep neural networks (DNNs) for medical images are extremely vulnerable to adversarial examples (AEs), which poses security concerns on clinical decision making. Luckily, medical AEs are also easy to detect in hierarchic…
Adversarial AttackDecision MakingGenerating Adversarial Attacks in the Latent Space
Adversarial attacks in the input (pixel) space typically incorporate noise margins such as $L_1$ or $L_{\infty}$-norm to produce imperceptibly perturbed data that confound deep learning networks. Such noise margins confi…
Adversarial AttackGenerative Adversarial Network