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

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.

[1]  Anjali Avinash Chandavale,et al.  Algorithm to Break Visual CAPTCHA , 2009, 2009 Second International Conference on Emerging Trends in Engineering & Technology.

[2]  Aren Jansen,et al.  Audio Set: An ontology and human-labeled dataset for audio events , 2017, 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[3]  Rob Fergus,et al.  Visualizing and Understanding Convolutional Networks , 2013, ECCV.

[4]  Jian Sun,et al.  Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[5]  Donald Geman,et al.  Visual Turing test for computer vision systems , 2015, Proceedings of the National Academy of Sciences.

[6]  Jürgen Schmidhuber,et al.  Connectionist temporal classification: labelling unsegmented sequence data with recurrent neural networks , 2006, ICML.

[7]  Gary Marcus,et al.  Deep Learning: A Critical Appraisal , 2018, ArXiv.

[8]  Manuel Blum,et al.  reCAPTCHA: Human-Based Character Recognition via Web Security Measures , 2008, Science.

[9]  Jitendra Malik,et al.  Recognizing objects in adversarial clutter: breaking a visual CAPTCHA , 2003, 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings..

[10]  A M Turing,et al.  Computing Machinery and Intelligence A.M. Turing , 2007 .

[11]  Jian Zhang,et al.  SQuAD: 100,000+ Questions for Machine Comprehension of Text , 2016, EMNLP.

[12]  Dumitru Erhan,et al.  Going deeper with convolutions , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[13]  Moni Naor,et al.  VERI CATION OF A HUMAN IN THE LOOP OR IDENTI CATION VIA THE TURING TEST , 1996 .

[14]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[15]  Xiaolin Hu,et al.  Defense Against Adversarial Attacks Using High-Level Representation Guided Denoiser , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[16]  Marek R. Ogiela,et al.  Application of knowledge‐based cognitive CAPTCHA in Cloud of Things security , 2018, Concurr. Comput. Pract. Exp..

[17]  Patrick D. McDaniel,et al.  Transferability in Machine Learning: from Phenomena to Black-Box Attacks using Adversarial Samples , 2016, ArXiv.

[18]  Jonathon Shlens,et al.  Explaining and Harnessing Adversarial Examples , 2014, ICLR.

[19]  Dawn Xiaodong Song,et al.  Delving into Transferable Adversarial Examples and Black-box Attacks , 2016, ICLR.

[20]  Fei-Fei Li,et al.  ImageNet: A large-scale hierarchical image database , 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition.

[21]  Bruce Carter.  Op Amps for Everyone , 2009 .

[22]  Joan Bruna,et al.  Intriguing properties of neural networks , 2013, ICLR.

[23]  David A. Wagner,et al.  Towards Evaluating the Robustness of Neural Networks , 2016, 2017 IEEE Symposium on Security and Privacy (SP).

[24]  Thomas M. Breuel,et al.  High-Performance OCR for Printed English and Fraktur Using LSTM Networks , 2013, 2013 12th International Conference on Document Analysis and Recognition.

[25]  Angelos D. Keromytis,et al.  I am Robot: (Deep) Learning to Break Semantic Image CAPTCHAs , 2016, 2016 IEEE European Symposium on Security and Privacy (EuroS&P).