HMM-based Attacks on Google's ReCAPTCHA with Continuous Visual and Audio Symbols

• Item type: JInfP(1)
• 公開日: 2015-11-15
• タイトル: HMM-based Attacks on Google's ReCAPTCHA with Continuous Visual and Audio Symbols
• タイトル / 言語: en
• タイトル: HMM-based Attacks on Google's ReCAPTCHA with Continuous Visual and Audio Symbols
• 言語: eng
• キーワード / 主題Scheme: Other
• キーワード / 主題: [Regular Papers] CAPTCHA, human interaction proof, hidden Markov model, continuous character/speech recognition
• 資源タイプ / 資源タイプ識別子: http://purl.org/coar/resource_type/c_6501
• 資源タイプ: journal article
• 著者所属: Graduate School of Informatics, Kyoto University
• 著者所属: Graduate School of Informatics, Kyoto University
• 著者所属: Graduate School of Informatics, Kyoto University
• 著者所属: Graduate School of Informatics, Kyoto University
• 著者所属(英): en
• 著者所属(英): Graduate School of Informatics, Kyoto University
• 著者所属(英): en
• 著者所属(英): Graduate School of Informatics, Kyoto University
• 著者所属(英): en
• 著者所属(英): Graduate School of Informatics, Kyoto University
• 著者所属(英): en
• 著者所属(英): Graduate School of Informatics, Kyoto University
• 著者名: Shotaro, Sano; Takuma, Otsuka; Katsutoshi, Itoyama; Hiroshi, G.,Okuno
• 著者名(英): Shotaro, Sano; Takuma, Otsuka; Katsutoshi, Itoyama; Hiroshi, G. Okuno
• 論文抄録 / 内容記述タイプ: Other
• 論文抄録 / 内容記述: CAPTCHAs distinguish humans from automated programs by presenting questions that are easy for humans but difficult for computers, e.g., recognition of visual characters or audio utterances. The state of the art research suggests that the security of visual and audio CAPTCHAs mainly lies in anti-segmentation techniques, because individual symbol recognition after segmentation can be solved with a high success rate with certain machine learning algorithms. Thus, most recent commercial CAPTCHAs present continuous symbols to prevent automated segmentation. We propose a novel framework that can automatically decode continuous CAPTCHAs and assess its effectiveness with actual CAPTCHA questions from Google's reCAPTCHA. Our framework is constructed on the basis of a sequence recognition method based on hidden Markov models (HMMs), which can be concisely implemented by using an off-the-shelf library HMM toolkit. This method concatenates several HMMs, each of which recognizes a symbol, to build a larger HMM that recognizes a question. Our experimental results reveal vulnerabilities in continuous CAPTCHAs because the solver cracks the visual and audio reCAPTCHA systems with 31.75% and 58.75% accuracy, respectively. We further propose guidelines to prevent possible attacking from HMM-based CAPTCHA solvers on the basis of synthetic experiments with simulated continuous CAPTCHAs.
• 論文抄録(英) / 内容記述タイプ: Other
• 論文抄録(英) / 内容記述: CAPTCHAs distinguish humans from automated programs by presenting questions that are easy for humans but difficult for computers, e.g., recognition of visual characters or audio utterances. The state of the art research suggests that the security of visual and audio CAPTCHAs mainly lies in anti-segmentation techniques, because individual symbol recognition after segmentation can be solved with a high success rate with certain machine learning algorithms. Thus, most recent commercial CAPTCHAs present continuous symbols to prevent automated segmentation. We propose a novel framework that can automatically decode continuous CAPTCHAs and assess its effectiveness with actual CAPTCHA questions from Google's reCAPTCHA. Our framework is constructed on the basis of a sequence recognition method based on hidden Markov models (HMMs), which can be concisely implemented by using an off-the-shelf library HMM toolkit. This method concatenates several HMMs, each of which recognizes a symbol, to build a larger HMM that recognizes a question. Our experimental results reveal vulnerabilities in continuous CAPTCHAs because the solver cracks the visual and audio reCAPTCHA systems with 31.75% and 58.75% accuracy, respectively. We further propose guidelines to prevent possible attacking from HMM-based CAPTCHA solvers on the basis of synthetic experiments with simulated continuous CAPTCHAs.
• 書誌レコードID / 収録物識別子タイプ: NCID
• 書誌レコードID / 収録物識別子: AA00700121
• 書誌情報: Journal of information processing; 巻 23, 号 6, p. 814-826, 発行日 2015-11-15
• ISSN / 収録物識別子タイプ: ISSN
• ISSN / 収録物識別子: 1882-6652
• 出版者 / 言語: ja
• 出版者: 情報処理学会