paper-with-me

Papers

Constructing Unrestricted Adversarial Examples with Generative Models

2018-05-21 · NeurIPS 2018 12 · Yang Song, Rui Shu, Nate Kushman, Stefano Ermon

Adversarial examples are typically constructed by perturbing an existing data point within a small matrix norm, and current defense methods are focused on guarding against this type of attack. In this paper, we propose unrestricted adversarial examples, a new threat model where the attackers are not restricted to small norm-bounded perturbations. Different from perturbation-based attacks, we propose to synthesize unrestricted adversarial examples entirely from scratch using conditional generative models. Specifically, we first train an Auxiliary Classifier Generative Adversarial Network (AC-GAN) to model the class-conditional distribution over data samples. Then, conditioned on a desired class, we search over the AC-GAN latent space to find images that are likely under the generative model and are misclassified by a target classifier. We demonstrate through human evaluation that unrestricted adversarial examples generated this way are legitimate and belong to the desired class. Our empirical results on the MNIST, SVHN, and CelebA datasets show that unrestricted adversarial examples can bypass strong adversarial training and certified defense methods designed for traditional adversarial attacks.

📄 PDF Abstract BibTeX arXiv:1805.07894

Code (1)

ermongroup/generative_adversary 공식 구현 tf

Tasks

Generative Adversarial Network

Similar Papers 제목 키워드 기반

Synthesizing Unrestricted False Positive Adversarial Objects Using Generative Models

2020-05-19 · Martin Kotuliak, Sandro E. Schoenborn, Andrei Dan

Adversarial examples are data points misclassified by neural networks. Originally, adversarial examples were limited to adding small perturbations to a given image. Recent work introduced the generalized concept of unres…

Objectobject-detectionObject Detection

AdvDiff: Generating Unrestricted Adversarial Examples using Diffusion Models

2023-07-24 · Xuelong Dai, Kaisheng Liang, Bin Xiao

Unrestricted adversarial attacks present a serious threat to deep learning models and adversarial defense techniques. They pose severe security problems for deep learning applications because they can effectively bypass …

Adversarial AttackAdversarial Defense

Fine-grained Synthesis of Unrestricted Adversarial Examples

2019-11-20 · Omid Poursaeed, Tianxing Jiang, Yordanos Goshu, Harry Yang 외

We propose a novel approach for generating unrestricted adversarial examples by manipulating fine-grained aspects of image generation. Unlike existing unrestricted attacks that typically hand-craft geometric transformati…

Image Generationobject-detectionObject DetectionSemantic Segmentation

AdvSPADE: Realistic Unrestricted Attacks for Semantic Segmentation

2019-10-06 · Guangyu Shen, Chengzhi Mao, Junfeng Yang, Baishakhi Ray

Due to the inherent robustness of segmentation models, traditional norm-bounded attack methods show limited effect on such type of models. In this paper, we focus on generating unrestricted adversarial examples for seman…

Adversarial AttackSegmentationSemantic Segmentation

Content-based Unrestricted Adversarial Attack

2023-05-18 · NeurIPS 2023 11

Unrestricted adversarial attacks typically manipulate the semantic content of an image (e.g., color or texture) to create adversarial examples that are both effective and photorealistic, demonstrating their ability to de…

Adversarial Attack