GreedyFool: Distortion-Aware Sparse Adversarial Attack

Dong, Xiaoyi; Chen, Dongdong; Bao, Jianmin; Qin, Chuan; Liu, Yuan; Zhang, Weiming; Yu, Nenghai; Chen, Dong

doi:10.48550/arxiv.2010.13773

Cited by 8 publications

(5 citation statements)

References 31 publications

(57 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Dong et al [66] proposed a so-called GreedyFool algorithm that performs a sparse distortion in the input image based on gradients of its pixels. With improved sparsity, the perceptibly of their gradient-based perturbations becomes lower.…”

Section: A Advanced Gradient Based Attacksmentioning

confidence: 99%

Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Survey

2018

View full text Add to dashboard Cite

Deep learning is at the heart of the current rise of artificial intelligence. In the field of Computer Vision, it has become the workhorse for applications ranging from self-driving cars to surveillance and security. Whereas deep neural networks have demonstrated phenomenal success (often beyond human capabilities) in solving complex problems, recent studies show that they are vulnerable to adversarial attacks in the form of subtle perturbations to inputs that lead a model to predict incorrect outputs. For images, such perturbations are often too small to be perceptible, yet they completely fool the deep learning models. Adversarial attacks pose a serious threat to the success of deep learning in practice. This fact has recently lead to a large influx of contributions in this direction. This article presents the first comprehensive survey on adversarial attacks on deep learning in Computer Vision. We review the works that design adversarial attacks, analyze the existence of such attacks and propose defenses against them. To emphasize that adversarial attacks are possible in practical conditions, we separately review the contributions that evaluate adversarial attacks in the real-world scenarios. Finally, drawing on the reviewed literature, we provide a broader outlook of this research direction.

show abstract

Section: A Advanced Gradient Based Attacksmentioning

confidence: 99%

Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Survey

2018

View full text Add to dashboard Cite

show abstract

“…The sparse adversarial attacks are compared with the stateof-the-art attacks i.e. C&W [6] Corner Search [26] Sparse Fool [25], Greedy Fool [27] and FGSM [5]. C&W [6] is considered to generate adversarial examples with minimum ℓ 2 noise, yet it is impractical because of its high number of iterations [7], [8].…”

Section: Experimental Settings and Resultsmentioning

confidence: 99%

“…Sparse attacks have been recently introduced in the field of adversarial attacks. Some of the early sparse attacks in adversarial setting includes JSMA [24], Sparse Fool [25], Corner Search [26] and Greedy Fool [27]. Sparse Fool [25] disrupts the geometrical properties of the images whereas, Corner Search [26] aims at minimizing the distance of the perturbation to the original image.…”

Section: Related Workmentioning

confidence: 99%

Adversarial Attack Using Sparse Representation of Feature Maps

Jahangir

2022

IEEE Access

View full text Add to dashboard Cite

Deep neural networks can be fooled by small imperceptible perturbations called adversarial examples. Although these examples are carefully crafted, they involve two major concerns. In some cases, adversarial examples generated are much larger than minimal adversarial perturbations while in others the attack method involves an extensive number of iterations making it infeasible. Moreover, the sparse attacks are either too complex or are not sparse enough to achieve imperceptibility. Therefore, attacks designed should be fast and minimum in terms of ℓ 2 -norm. In this research, we used a dictionary learning technique to generate sparse adversarial examples based on feature maps of target images. We present two novel algorithms to tune the dictionary learning process and feature map selection. The results on MNIST and Imagenet show our attack is better or competitive with the state-of-the-art methods. We also compared our method with sparse attacks recently introduced in literature. As a result, we have achieved comparable attack success rate when compared to the state-of-the-art with smaller ℓ 2 -norm. We also tested the efficacy of our attack in the presence of defense mechanisms and none of the defenses were able to combat the effect of our proposed attack INDEX TERMS adversarial attacks, dictionary learning, sparse representation

show abstract

“…In order to resist steganalyzer, Dong et al [12] proposed using generative adversarial network to generate a distortion map. However, this method has some disadvantages, such as slow generation speed and unable to migrate.…”

Section: Steganography-based Adversarial Attackmentioning

confidence: 99%

Distortion-aware adversarial attack against steganalysis detectors

Zeng

2022

Second International Symposium on Computer Technology and Information Science (ISCTIS 2022)

View full text Add to dashboard Cite

This paper analyzes the similarity between steganography and adversarial attack, and then analyzes the attack and defense stage of adversarial samples from the perspective of steganography, which provides a broader idea for researchers in this field. This paper validates the efficiency of steganography on help resisting adversarial attack and proposes a steganalysis based method to enhance the adversarial attack against steganalysis detectors with the help of a distortion function. We combine the distortion map with gradient information to select the disturbed pixels in each attack iteration to generate adversarial samples that can bypass steganalysis detectors. The results show that steganography technology can help detecting normal adversarial samples, and our enhanced adversarial samples achieve a much higher transparency rate against our steganography based method than other normal adversarial samples.

show abstract

GreedyFool: Distortion-Aware Sparse Adversarial Attack

Cited by 8 publications

References 31 publications

Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Survey

Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Survey

Adversarial Attack Using Sparse Representation of Feature Maps

Distortion-aware adversarial attack against steganalysis detectors

Contact Info

Product

Resources

About