Journal
IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY
Volume 12, Issue 11, Pages 2640-2653Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TIFS.2017.2718479
Keywords
CAPTCHA; deep learning; CNN; adversarial examples; HIP
Funding
- U.K. Engineering and Physical Sciences Research Council [EP/M013375/1]
- Israeli Ministry of Science and Technology [3-11858]
- Engineering and Physical Sciences Research Council [EP/M013375/1] Funding Source: researchfish
- EPSRC [EP/M013375/1] Funding Source: UKRI
Ask authors/readers for more resources
Recent advances in deep learning (DL) allow for solving complex AI problems that used to be considered very hard. While this progress has advanced many fields, it is considered to be bad news for Completely Automated Public Turing tests to tell Computers and Humans Apart (CAPTCHAs), the security of which rests on the hardness of some learning problems. In this paper, we introduce DeepCAPTCHA, a new and secure CAPTCHA scheme based on adversarial examples, an inherit limitation of the current DL networks. These adversarial examples are constructed inputs, either synthesized from scratch or computed by adding a small and specific perturbation called adversarial noise to correctly classified items, causing the targeted DL network to misclassify them. We show that plain adversarial noise is insufficient to achieve secure CAPTCHA schemes, which leads us to introduce immutable adversarial noise-an adversarial noise that is resistant to removal attempts. In this paper, we implement a proof of concept system, and its analysis shows that the scheme offers high security and good usability compared with the best previously existing CAPTCHAs.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available