paper-with-me

홈 › Papers

SemanticAdv: Generating Adversarial Examples via Attribute-conditioned Image Editing

2020-08-01 · ECCV 2020 8 · Haonan Qiu, Chaowei Xiao, Lei Yang, Xinchen Yan, Honglak Lee, Bo Li

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.

📄 PDF Abstract BibTeX

Code (1)

AI-secure/SemanticAdv pytorch

Tasks

Adversarial AttackAttributeFace RecognitionSemantic Segmentation

Similar Papers 제목 키워드 기반

SemanticAdv: Generating Adversarial Examples via Attribute-conditional Image Editing

2019-06-19 · Haonan Qiu, Chaowei Xiao, Lei Yang, Xinchen Yan 외

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 Verification

EdgeFool: An Adversarial Image Enhancement Filter

2019-10-27 · Ali Shahin Shamsabadi, Changjae Oh, Andrea Cavallaro

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 Enhancement

Facial Attributes: Accuracy and Adversarial Robustness

2018-01-04 · Andras Rozsa, Manuel Günther, Ethan M. Rudd, Terrance E. Boult

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 Classification

SemDiff: Generating Natural Unrestricted Adversarial Examples via Semantic Attributes Optimization in Diffusion Models

2025-04-16 · Zeyu Dai, Shengcai Liu, Rui He, Jiahao Wu 외

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 Attack

Attribute-conditioned Layout GAN for Automatic Graphic Design

2020-09-11 · Jianan Li, Jimei Yang, Jianming Zhang, Chang Liu 외

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