{"type":"ScholarlyArticle","title":"Latent Regularized Generative Dual Adversarial Network For Abnormal Detection","authors":[{"name":"Chengwei Chen","slug":"chengwei-chen","given":"Chengwei","family":"Chen","affiliation":"East China Normal University"},{"name":"Jing Liu","slug":"jing-liu","given":"Jing","family":"Liu","affiliation":"East China Normal University"},{"name":"Yuan Xie","slug":"yuan-xie","given":"Yuan","family":"Xie","affiliation":"East China Normal University"},{"name":"Yin Xiao Ban","slug":"yin-xiao-ban","given":"Yin Xiao","family":"Ban","affiliation":"East China Normal University"},{"name":"Chunyun Wu","slug":"chunyun-wu","given":"Chunyun","family":"Wu","affiliation":"East China Normal University"},{"name":"Yiqing Tao","slug":"yiqing-tao","given":"Yiqing","family":"Tao","affiliation":"East China Normal University"},{"name":"Haichuan Song","slug":"haichuan-song","given":"Haichuan","family":"Song","affiliation":"East China Normal University"}],"abstract":"With the development of adversarial attack in deep learning, it is critical for abnormal detector to not only discover the out-of-distribution samples but also provide defence against the adversarial attacker. Since few previous universal detector is known to work well on both tasks, we consider against both scenarios by constructing a robust and effective technique, where one sample could be regarded as the abnormal sample if it exhibits a higher image reconstruction error. Due to the training instability issues existed in previous generative adversarial networks (GANs) based methods, in this paper we propose a dual auxiliary autoencoder to make a tradeoff between the capability of generator and discriminator, leading to a more stable training process and high-quality image reconstruction. Moreover, to generate discriminative and robust latent representations, the mutual information estimator regarded as latent regularizer is adopted to extract the most unique information of target class. Overall, our generative dual adversarial network simultaneously optimizes the image reconstruction space and latent space to improve the performance. Experiments show that our model has the clear superiority over cutting edge semi-supervised abnormal detectors and achieves the state-of-the-art results on the datasets.","doi":"10.24963/ijcai.2020/106","url":"https://ijcai.org/proceedings/2020/106","pdf":"https://ijcai.org/proceedings/2020/0106.pdf","markdown":"https://ijcai.org/proceedings/2020/106.md","bibtex":"https://ijcai.org/proceedings/2020/bibtex/106","volume":{"slug":"2020","title":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2020","url":"https://ijcai.org/proceedings/2020/","year":2020,"location":"Yokohama","dates":"January 2021 (postponed from 11-17 July 2020)","editors":"Christian Bessiere","isbn":"978-0-9992411-6-5","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2020"},"section":"Computer Vision","track":"Main track","number":106,"pages":{"first":760,"last":766},"keywords":["Computer Vision: Recognition: Detection, Categorization, Indexing, Matching, Retrieval, Semantic Interpretation","Computer Vision: 2D and 3D Computer Vision"],"videos":[{"label":"Video","url":"https://videos.ijcai20.org/24435/file_24435.m3u8","length_sec":270,"provider":"hls"}],"references":[{"position":1,"raw":"[Belghazi et al., 2018] Mohamed Ishmael Belghazi, Aris- tide Baratin, Sai Rajeswar, Sherjil Ozair, Yoshua Ben- gio, Aaron Courville, and R Devon Hjelm. Mine: mutual information neural estimation. arXiv preprint arXiv:1801.04062, 2018.","title":"Mohamed Ishmael Belghazi, Aristide Baratin","authors":"Belghazi","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Bengio and Mariéthoz, 2004] Samy Bengio and Johnny Mariéthoz. A statistical significance test for person au- thentication. In Proceedings of Odyssey 2004: The Speaker and Language Recognition Workshop, number CONF, 2004.","title":"A statistical significance test for person authentication","authors":"Samy Bengio, Johnny Mariéthoz","year":"2004","venue":"Proceedings of Odyssey 2004: The Speaker and Language Recognition Workshop, number CONF","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Boulkenafet et al., 2015] Zinelabidine Boulkenafet, Jukka Komulainen, and Abdenour Hadid. Face anti-spoofing based on color texture analysis. In 2015 IEEE inter- national conference on image processing (ICIP), pages 2636-2640. IEEE, 2015.","title":"Face anti-spoofing based on color texture analysis","authors":"Boulkenafet","year":"2015","venue":"IEEE international conference on image processing (ICIP)","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Boulkenafet et al., 2016] Zinelabidine Boulkenafet, Jukka Komulainen, and Abdenour Hadid. Face spoofing de- tection using colour texture analysis. IEEE Transactions on Information Forensics and Security, 11(8):1818-1830, 2016.","title":"Face spoofing detection using colour texture analysis","authors":"Boulkenafet","year":"2016","venue":"IEEE Transactions on Information Forensics and Security","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Chalapathy et al., 2017] Raghavendra Chalapathy, Aditya Krishna Menon, and Sanjay Chawla. Ro- bust, deep and inductive anomaly detection. In Joint European Conference on Machine Learning and Knowl- edge Discovery in Databases, pages 36-51. Springer, 2017.","title":"Robust, deep and inductive anomaly detection","authors":"Raghavendra Chalapathy, Aditya Krishna Menon, Sanjay Chawla","year":"2017","venue":"Joint European Conference on Machine Learning and Knowledge Discovery in Databases","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Chalapathy et al., 2018] Raghavendra Chalapathy, Aditya Krishna Menon, and Sanjay Chawla. Anomaly detection using one-class neural networks. arXiv preprint arXiv:1802.06360, 2018.","title":"Anomaly detection using one-class neural networks","authors":"Raghavendra Chalapathy, Aditya Krishna Menon, Sanjay Chawla","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Chingovska et al., 2012] Ivana Chingovska, André Anjos, and Sébastien Marcel. On the effectiveness of local bi- nary patterns in face anti-spoofing. In 2012 BIOSIG- proceedings of the international conference of biometrics special interest group (BIOSIG), pages 1-7. IEEE, 2012.","title":"On the effectiveness of local binary patterns in face anti-spoofing","authors":"Ivana Chingovska, André Anjos, Sébastien Marcel","year":"2012","venue":"BIOSIGproceedings of the international conference of biometrics special interest group (BIOSIG)","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Goodfellow et al., 2014] Ian J Goodfellow, Jonathon Shlens, and Christian Szegedy. Explaining and harnessing adversarial examples. arXiv preprint arXiv:1412.6572, 2014.","title":"Explaining and harnessing adversarial examples","authors":"Ian J Goodfellow, Jonathon Shlens, Christian Szegedy","year":"2014","venue":null,"doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Jourabloo et al., 2018] Amin Jourabloo, Yaojie Liu, and Xi- aoming Liu. Face de-spoofing: Anti-spoofing via noise modeling. In Proceedings of the ECCV, pages 290-306, 2018.","title":"Face de-spoofing: Anti-spoofing via noise modeling","authors":"Amin Jourabloo, Yaojie Liu, Xiaoming Liu","year":"2018","venue":"Proceedings of the ECCV","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Kurakin et al., 2016] Alexey Kurakin, Ian Goodfellow, and Samy Bengio. Adversarial examples in the physical world. arXiv preprint arXiv:1607.02533, 2016.","title":"Adversarial examples in the physical world","authors":"Alexey Kurakin, Ian Goodfellow, Samy Bengio","year":"2016","venue":null,"doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Liang et al., 2018] Bin Liang, Hongcheng Li, Miaoqiang Su, Xirong Li, Wenchang Shi, and XiaoFeng Wang. De- tecting adversarial image examples in deep neural net- works with adaptive noise reduction. IEEE Transactions on Dependable and Secure Computing, 2018.","title":"Detecting adversarial image examples in deep neural networks with adaptive noise reduction","authors":"Liang","year":"2018","venue":"IEEE Transactions on Dependable and Secure Computing","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Liu et al., 2018] Yaojie Liu, Amin Jourabloo, and Xiaom- ing Liu. Learning deep models for face anti-spoofing: Bi- nary or auxiliary supervision. In Proceedings of the IEEE Conference on CVPR, pages 389-398, 2018.","title":"Learning deep models for face anti-spoofing: Bi-nary or auxiliary supervision","authors":"Liu","year":"2018","venue":"Proceedings of the IEEE Conference on CVPR","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Moosavi-Dezfooli et al., 2016] Seyed-Mohsen Moosavi- Dezfooli, Alhussein Fawzi, and Pascal Frossard. Deep- fool: a simple and accurate method to fool deep neural networks. In Proceedings of the IEEE conference on CVPR, pages 2574-2582, 2016.","title":"Deepfool: a simple and accurate method to fool deep neural networks","authors":"Seyed-Mohsen Moosavi-Dezfooli, Alhussein Fawzi, Pascal Frossard","year":"2016","venue":"Proceedings of the IEEE conference on CVPR","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Nowozin et al., 2016] Sebastian Nowozin, Botond Cseke, and Ryota Tomioka. f-gan: Training generative neural samplers using variational divergence minimization. In Advances in neural information processing systems, pages 271-279, 2016.","title":"f-gan: Training generative neural samplers using variational divergence minimization","authors":"Sebastian Nowozin, Botond Cseke, Ryota Tomioka","year":"2016","venue":"Advances in neural information processing systems","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Patel et al., 2016] Keyurkumar Patel, Hu Han, and Anil K Jain. Secure face unlock: Spoof detection on smartphones. IEEE Transactions on Information Forensics and Security, 11(10):2268-2283, 2016.","title":"Secure face unlock: Spoof detection on smartphones","authors":"Patel","year":"2016","venue":"IEEE Transactions on Information Forensics and Security","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Perera et al., 2019] Pramuditha Perera, Ramesh Nallapati, and Bing Xiang. Ocgan: One-class novelty detection using gans with constrained latent representations. In Proceed- ings of the IEEE Conference on CVPR, pages 2898-2906, 2019.","title":"Ocgan: One-class novelty detection using gans with constrained latent representations","authors":"Perera","year":"2019","venue":"Proceedings of the IEEE Conference on CVPR","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Ruff et al., 2018] Lukas Ruff, Robert Vandermeulen, Nico Goernitz, Lucas Deecke, Shoaib Ahmed Siddiqui, Alexan- der Binder, Emmanuel Müller, and Marius Kloft. Deep one-class classification. In International conference on machine learning, pages 4393-4402, 2018.","title":"Deep one-class classification","authors":"Lukas Ruff, Robert Vandermeulen, Nico Goernitz, Lucas Deecke, Ahmed Shoaib, Alexander Siddiqui, Emmanuel Binder, Marius Müller, Kloft","year":"2018","venue":"International conference on machine learning","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Rushe and Mac Namee, 2019] Ellen Rushe and Brian Mac Namee. Anomaly detection in raw audio using deep autoregressive networks. In ICASSP 2019-2019 IEEE, pages 3597-3601. IEEE, 2019.","title":"Anomaly detection in raw audio using deep autoregressive networks","authors":"Mac Rushe, Ellen Namee, Brian Rushe, Namee Mac","year":"2019","venue":"ICASSP 2019-2019 IEEE","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Sabokrou et al., 2018] Mohammad Sabokrou, Mohammad Khalooei, Mahmood Fathy, and Ehsan Adeli. Adver- sarially learned one-class classifier for novelty detection. In Proceedings of the IEEE Conference on CVPR, pages 3379-3388, 2018.","title":"Adversarially learned one-class classifier for novelty detection","authors":"Mohammad Sabokrou, Mohammad Khalooei, Mahmood Fathy, Ehsan Adeli","year":"2018","venue":"Proceedings of the IEEE Conference on CVPR","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Stallkamp et al., 2011] Johannes Stallkamp, Marc Schlips- ing, Jan Salmen, and Christian Igel. The german traffic sign recognition benchmark: A multi-class classification competition. In IJCNN, volume 6, page 7, 2011.","title":"The german traffic sign recognition benchmark: A multi-class classification competition","authors":"Johannes Stallkamp, Marc Schlipsing, Jan Salmen, Christian Igel","year":"2011","venue":"IJCNN","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Tramèr et al., 2017] Florian Tramèr, Alexey Kurakin, Nico- las Papernot, Ian Goodfellow, Dan Boneh, and Patrick Mc- Daniel. Ensemble adversarial training: Attacks and de- fenses. arXiv preprint arXiv:1705.07204, 2017.","title":"Ensemble adversarial training: Attacks and defenses","authors":"Florian Tramèr, Alexey Kurakin, Nicolas Papernot, Ian Goodfellow, Dan Boneh, Patrick Mc-Daniel","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Tu et al., 2019] Xiaoguang Tu, Jian Zhao, Mei Xie, Guodong Du, Hengsheng Zhang, Jianshu Li, Zheng Ma, and Jiashi Feng. Learning generalizable and identity- discriminative representations for face anti-spoofing. arXiv preprint arXiv:1901.05602, 2019.","title":"Learning generalizable and identitydiscriminative representations for face anti-spoofing","authors":"Xiaoguang Tu, Jian Zhao, Mei Xie, Guodong Du, Hengsheng Zhang, Jianshu Li, Zheng Ma, Jiashi Feng","year":"2019","venue":null,"doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Yang et al., 2019] Xu Yang, Cheng Deng, Feng Zheng, Junchi Yan, and Wei Liu. Deep spectral clustering using dual autoencoder network. In Proceedings of the IEEE Conference on CVPR, pages 4066-4075, 2019.","title":"Deep spectral clustering using dual autoencoder network","authors":"Xu Yang, Cheng Deng, Feng Zheng, Junchi Yan, Wei Liu","year":"2019","venue":"Proceedings of the IEEE Conference on CVPR","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}