SemanticAdv: Generating Adversarial Examples via Attribute-conditioned Image Editing
Deep neural networks (DNNs) have achieved great successes in various vision applications due to their strong expressive power. However, recent studies have shown that DNNs are vulnerable to adversarial examples which are manipulated instances targeting to mislead DNNs to make incorrect predictions. Currently, most such adversarial examples try to guarantee ``subtle perturbation"" by limiting the $L_p$ norm of the perturbation. In this paper, we propose SemanticAdv to generate a new type of semantically realistic adversarial examples via attribute-conditioned image editing. Compared to existing methods, our SemanticAdv enables fine-grained analysis and evaluation of DNNs with input variations in the attribute space. We conduct comprehensive experiments to show that our adversarial examples not only exhibit semantically meaningful appearances but also achieve high targeted attack success rates under both whitebox and blackbox settings. Moreover, we show that the existing pixel-based and attribute-based defense methods fail to defend against our attribute-conditioned adversarial examples. We demonstrate the applicability of SemanticAdv on both face recognition and general street-view images to show its generalization. Such non-$L_p$ bounded adversarial examples with controlled attribute manipulation can shed light on further understanding about vulnerabilities of DNNs as well as novel defense approaches.
Code (1)
Tasks
Adversarial AttackAttributeFace RecognitionSemantic SegmentationSimilar Papers 제목 키워드 기반
SemanticAdv: Generating Adversarial Examples via Attribute-conditional Image Editing
Deep neural networks (DNNs) have achieved great success in various applications due to their strong expressive power. However, recent studies have shown that DNNs are vulnerable to adversarial examples which are manipula…
AttributeFace RecognitionFace VerificationEdgeFool: An Adversarial Image Enhancement Filter
Adversarial examples are intentionally perturbed images that mislead classifiers. These images can, however, be easily detected using denoising algorithms, when high-frequency spatial perturbations are used, or can be no…
DenoisingImage EnhancementFacial Attributes: Accuracy and Adversarial Robustness
Facial attributes, emerging soft biometrics, must be automatically and reliably extracted from images in order to be usable in stand-alone systems. While recent methods extract facial attributes using deep neural network…
Adversarial RobustnessAttributeGeneral ClassificationSemDiff: Generating Natural Unrestricted Adversarial Examples via Semantic Attributes Optimization in Diffusion Models
Unrestricted adversarial examples (UAEs), allow the attacker to create non-constrained adversarial examples without given clean samples, posing a severe threat to the safety of deep learning models. Recent works utilize …
Adversarial AttackAttribute-conditioned Layout GAN for Automatic Graphic Design
Modeling layout is an important first step for graphic design. Recently, methods for generating graphic layouts have progressed, particularly with Generative Adversarial Networks (GANs). However, the problem of specifyin…
AttributeLayout Generation