Open-Set Adversarial Defense

Shao, Rui; Perera, Pramuditha; Yuen, Pong C.; Patel, Vishal M.

doi:10.1007/978-3-030-58520-4_40

Cited by 23 publications

(11 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There are also examples providing specialized defenses for computer vision tasks other than standard classification, e.g. tracking [440], open-set recognition [441], face recognition [442]. Goldblum et al [443] proposed a method to infer robust models for few-shot classification tasks based on adversarially robust meta-learners.…”

Section: E Miscellaneous Methodsmentioning

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: E Miscellaneous Methodsmentioning

confidence: 99%

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

2018

View full text Add to dashboard Cite

show abstract

“…Zhang et al [39] induce a sparsity constraint on features for open set classification. Further, Shao et al [36] defend against open set adversarial attacks.…”

Section: Related Workmentioning

confidence: 99%

Anomaly Detection-Based Unknown Face Presentation Attack Detection

Baweja¹,

Oza²,

Perera³

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

Anomaly detection-based spoof attack detection is a recent development in face Presentation Attack Detection (fPAD), where a spoof detector is learned using only nonattacked images of users. These detectors are of practical importance as they are shown to generalize well to new attack types. In this paper, we present a deep-learning solution for anomaly detection-based spoof attack detection where both classifier and feature representations are learned together end-to-end. First, we introduce a pseudonegative class during training in the absence of attacked images. The pseudo-negative class is modeled using a Gaussian distribution whose mean is calculated by a weighted running mean. Secondly, we use pairwise confusion loss to further regularize the training process. The proposed approach benefits from the representation learning power of the CNNs and learns better features for fPAD task as shown in our ablation study. We perform extensive experiments on four publicly available datasets: Replay-Attack, Rose-Youtu, OULU-NPU and Spoof in Wild to show the effectiveness of the proposed approach over the previous methods. Code is available at: https://github.com/ yashasvi97/IJCB2020_anomaly

show abstract

“…This stream has been repeatedly validated as effective, especially under strong adaptive attacks in the challenging white-box setting [4]. It has been widely used as a fundamental defense backbone [5,6,7].…”

Section: Introductionmentioning

confidence: 99%

Error Diffusion Halftoning Against Adversarial Examples

Patel

2021

2021 IEEE International Conference on Image Processing (ICIP)

Self Cite

View full text Add to dashboard Cite

Adversarial examples contain carefully crafted perturbations that can fool deep neural networks (DNNs) into making wrong predictions. Enhancing the adversarial robustness of DNNs has gained considerable interest in recent years. Although image transformation-based defenses were widely considered at an earlier time, most of them have been defeated by adaptive attacks. In this paper, we propose a new image transformation defense based on error diffusion halftoning, and combine it with adversarial training to defend against adversarial examples. Error diffusion halftoning projects an image into a 1-bit space and diffuses quantization error to neighboring pixels. This process can remove adversarial perturbations from a given image while maintaining acceptable image quality in the meantime in favor of recognition. Experimental results demonstrate that the proposed method is able to improve adversarial robustness even under advanced adaptive attacks, while most of the other image transformation-based defenses do not. We show that a proper image transformation can still be an effective defense approach.

show abstract

Open-Set Adversarial Defense

Cited by 23 publications

References 50 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

Anomaly Detection-Based Unknown Face Presentation Attack Detection

Error Diffusion Halftoning Against Adversarial Examples

Contact Info

Product

Resources

About