paper-with-me

Papers

blessing in disguise: Designing Robust Turing Test by Employing Algorithm Unrobustness

2019-04-22 · Jiaming Zhang, Jitao Sang, Kaiyuan Xu, Shangxi Wu, Yongli Hu, Yanfeng Sun, Jian Yu

Turing test was originally proposed to examine whether machine's behavior is indistinguishable from a human. The most popular and practical Turing test is CAPTCHA, which is to discriminate algorithm from human by offering recognition-alike questions. The recent development of deep learning has significantly advanced the capability of algorithm in solving CAPTCHA questions, forcing CAPTCHA designers to increase question complexity. Instead of designing questions difficult for both algorithm and human, this study attempts to employ the limitations of algorithm to design robust CAPTCHA questions easily solvable to human. Specifically, our data analysis observes that human and algorithm demonstrates different vulnerability to visual distortions: adversarial perturbation is significantly annoying to algorithm yet friendly to human. We are motivated to employ adversarially perturbed images for robust CAPTCHA design in the context of character-based questions. Three modules of multi-target attack, ensemble adversarial training, and image preprocessing differentiable approximation are proposed to address the characteristics of character-based CAPTCHA cracking. Qualitative and quantitative experimental results demonstrate the effectiveness of the proposed solution. We hope this study can lead to the discussions around adversarial attack/defense in CAPTCHA design and also inspire the future attempts in employing algorithm limitation for practical usage.

📄 PDF Abstract BibTeX arXiv:1904.09804

Code (0)

등록된 구현이 없습니다.

Tasks

Adversarial Attack

Similar Papers 제목 키워드 기반

Classifier Adaptation at Prediction Time

2015-06-01 · CVPR 2015 6 · Amelie Royer, Christoph H. Lampert

Classifiers for object categorization are usually evaluated by their accuracy on a set of i.i.d. test examples. This provides us with an estimate of the expected error when applying the classifiers to a single new image.…

Object CategorizationPrediction

Strategic Classification is Causal Modeling in Disguise

2019-10-23 · ICML 2020 1 · John Miller, Smitha Milli, Moritz Hardt

Consequential decision-making incentivizes individuals to strategically adapt their behavior to the specifics of the decision rule. While a long line of work has viewed strategic adaptation as gaming and attempted to mit…

Causal InferenceClassificationDecision MakingGeneral Classification

Towards Attribute-Entangled Controllable Text Generation: A Pilot Study of Blessing Generation

2022-10-29 · Shulin Huang, Shirong Ma, Yinghui Li, Yangning Li 외

Controllable Text Generation (CTG) has obtained great success due to its fine-grained generation ability obtained by focusing on multiple attributes. However, most existing CTG researches overlook how to utilize the attr…

AttributeDiversityText Generation

Catastrophic Overfitting: A Potential Blessing in Disguise

2024-02-28 · Mengnan Zhao, Lihe Zhang, Yuqiu Kong, BaoCai Yin

Fast Adversarial Training (FAT) has gained increasing attention within the research community owing to its efficacy in improving adversarial robustness. Particularly noteworthy is the challenge posed by catastrophic over…

Adversarial Robustness

Sejong Face Database: A Multi-Modal Disguise Face Database

2021-06-14 · Usman Cheema, Seungbin Moon

Commercial application of facial recognition demands robustness to a variety of challenges such as illumination, occlusion, spoofing, disguise, etc. Disguised face recognition is one of the emerging issues for access con…

Face DetectionFace Recognition