Robust Text CAPTCHAs Using Adversarial Examples

Shao, Rulin; Shi, Zhouxing; Yi, Jinfeng; Chen, Pin-Yu; Hsieh, Cho‐Jui

doi:10.1109/bigdata55660.2022.10021100

Cited by 13 publications

(19 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recently, ViT [14] receives notable attention for its outstanding performance on various tasks. Meanwhile, some works [38,49] have demonstrated that ViT models exhibit lower adversarial transferability than CNNs when used as surrogates, and a recent work [43] argues that this is because the current attacks are not strong enough to fully exploit the transferability potential of ViT. Complementarily, we provide a different viewpoint that the transferability of ViT may have been restrained by its own training paradigm.…”

Section: Analyses and Discussionmentioning

confidence: 81%

Preface: Celebrating the 70th Anniversary of School of Mechanical Science and Engineering, Huazhong University of Science and Technology

Huang

Yin

2022

Sci. China Technol. Sci.

View full text Add to dashboard Cite

The shifted fractional trapezoidal rule (SFTR) with a special shift is adopted to construct a finite difference scheme for the time-fractional Allen-Cahn (tFAC) equation. Some essential key properties of the weights of SFTR are explored for the first time. Based on these properties, we rigorously demonstrate the discrete energy decay property and maximum-principle preservation for the scheme. Numerical investigations show that the scheme can resolve the intrinsic initial singularity of such nonlinear fractional equations as tFAC equation on uniform meshes without any correction. Comparison with the classic fractional BDF2 and L2-1 σ method further validates the superiority of SFTR in solving the tFAC equation. Experiments concerning both discrete energy decay and discrete maximum-principle also verify the correctness of the theoretical results.

show abstract

Section: Analyses and Discussionmentioning

confidence: 81%

Preface: Celebrating the 70th Anniversary of School of Mechanical Science and Engineering, Huazhong University of Science and Technology

Huang

Yin

2022

Sci. China Technol. Sci.

View full text Add to dashboard Cite

show abstract

“…e adversarial example is the weakness of the ML classifier, and it can be used as a tool to defend against the inference attack launched by the ML classifiers. Many works including [7][8][9][10][11][12][13] have been proposed to defend against inference attack using the idea of the adversarial example. Liu et al [7] proposed the stealth algorithm of elaborating adversarial examples to resist the automatic detection system based on the Faster RCNN framework.…”

Section: Related Workmentioning

confidence: 99%

“…Liu et al [11] proposed the schemes to protect the privacy of the Internet user, which used the idea of adversarial example. Shao et al [12] proposed the robust text CAPTCHAs scheme based on the adversarial example. Li and Lin [13] proposed to use adversarial perturbation for face deidentification.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Towards Attack to MemGuard with Nonlocal-Means Method

Xie

Pei

2022

Security and Communication Networks

View full text Add to dashboard Cite

An adversarial example is the weakness of the machine learning (ML), and it can be utilized as the tool to defend against the inference attacks launched by ML classifiers. Jia et al. proposed MemGuard, which applied the idea of adversarial example to defend against membership inference attack. In a membership inference attack, the attacker attempts to infer whether a particular sample is in the training set of the target classifier, which may be a software or a service whose model parameters are unknown to the attacker. MemGuard does not tamper the training process of the target classifier, meanwhile achieving better tradeoff between the privacy and utility loss. However, many defenses of the adversarial example have been proposed, which decreases the effectiveness of the adversarial example. Inspired by the defenses of the adversarial example, we try to attack the MemGuard. As a result, we utilize the nonlocal-means method to do the attack by using the inherent relationship between neighbor entries to remove the added noise. Due to the low dimensionality of the confidence score vector, our attack avoids the high computation overhead of the nonlocal-means method. Besides, we use practical datasets to test our attack, and the experimental results demonstrate the effectiveness of our attack.

show abstract

“…Although Vision Transformer (ViT) seems promising for the vision tasks in terms of accuracy, it suffers from a few underlying problems like, a) Robustness against adversarial attacks Shao et al (2022); Mahmood et al (2021), and b) Extraction of local features ; Yuan et al (2021).…”

Section: Introductionmentioning

confidence: 99%