FDA: Feature Disruptive Attack

Ganeshan, Aditya; Boominathan, Vivek; Radhakrishnan, Venkatesh Babu

doi:10.1109/iccv.2019.00816

Cited by 80 publications

(41 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Similarly, Mor et al [177] study optimal strategies against generative adversarial attacks. A Feature Disruptive Attack was proposed in [178] that is targeted at disrupting the internal representation of models for the adversarial samples, instead of simply focusing on altering the prediction.…”

Section: G Miscellaneous 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: G Miscellaneous 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

“…More recently, attack methods applicable for tasks other than classification have been developed. For instance, [7] proposed the feature disruptive attack (FDA) method, which attempts to find perturbation from the intermediate features of a given model. These focus on the image classification task, and an in-depth study on vulnerability of image-to-image models for various tasks has not been conducted.…”

Section: Related Workmentioning

confidence: 99%

Deep Image Destruction: A Comprehensive Study on Vulnerability of Deep Image-to-Image Models against Adversarial Attacks

Choi¹,

Zhang²,

Kim³

et al. 2021

Preprint

View full text Add to dashboard Cite

Recently, the vulnerability of deep image classification models to adversarial attacks has been investigated. However, such an issue has not been thoroughly studied for image-to-image models that can have different characteristics in quantitative evaluation, consequences of attacks, and defense strategy. To tackle this, we present comprehensive investigations into the vulnerability of deep image-to-image models to adversarial attacks. For five popular image-toimage tasks, 16 deep models are analyzed from various standpoints such as output quality degradation due to attacks, transferability of adversarial examples across different tasks, and characteristics of perturbations. We show that unlike in image classification tasks, the performance degradation on image-to-image tasks can largely differ depending on various factors, e.g., attack methods and task objectives. In addition, we analyze the effectiveness of conventional defense methods used for classification models in improving the robustness of the image-to-image models.

show abstract

“…Further instances of the follow-up iterative algorithms are Variance-Reduced I-FGSM (vr-IGSM) [19] and PGD [13] etc. The above-mentioned algorithms and other recent works [20]- [25] compute image-specific adversarial perturbations which appear as insignificant noise to the human eye but completely confuse the models. Moosavi-Dezfooli et al [26] first demonstrated the possibility of fooling deep models simultaneously on a large number of images with Universal Adversarial Perturbations.…”

Section: A Adversarial Attacksmentioning

confidence: 99%

Orthogonal Deep Models as Defense Against Black-Box Attacks

et al. 2020

View full text Add to dashboard Cite

Deep learning has demonstrated state-of-the-art performance for a variety of challenging computer vision tasks. On one hand, this has enabled deep visual models to pave the way for a plethora of critical applications like disease prognostics and smart surveillance. On the other, deep learning has also been found vulnerable to adversarial attacks, which calls for new techniques to defend deep models against these attacks. Among the attack algorithms, the black-box schemes are of serious practical concern since they only need publicly available knowledge of the targeted model. We carefully analyze the inherent weakness of deep models in black-box settings where the attacker may develop the attack using a model similar to the targeted model. Based on our analysis, we introduce a novel gradient regularization scheme that encourages the internal representation of a deep model to be orthogonal to another, even if the architectures of the two models are similar. Our unique constraint allows a model to concomitantly endeavour for higher accuracy while maintaining near orthogonal alignment of gradients with respect to a reference model. Detailed empirical study verifies that controlled misalignment of gradients under our orthogonality objective significantly boosts a model's robustness against transferable black-box adversarial attacks. In comparison to regular models, the orthogonal models are significantly more robust to a range of l p norm bounded perturbations. We verify the effectiveness of our technique on a variety of large-scale models. INDEX TERMSDeep learning, adversarial examples, adversarial perturbations, orthogonal models, robust deep learning.

show abstract

FDA: Feature Disruptive Attack

Cited by 80 publications

References 42 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

Deep Image Destruction: A Comprehensive Study on Vulnerability of Deep Image-to-Image Models against Adversarial Attacks

Orthogonal Deep Models as Defense Against Black-Box Attacks

Contact Info

Product

Resources

About