{"type":"ScholarlyArticle","title":"IntensPure: Attack Intensity-aware Secondary Domain Adaptive Diffusion for Adversarial Purification","authors":[{"name":"Eun-Gi Lee","slug":"eun-gi-lee","given":"Eun-Gi","family":"Lee","affiliation":"Department of Artificial Intelligence Convergence , Chonnam National University , Gwangju , Korea"},{"name":"Moon Seok Lee","slug":"moon-seok-lee","given":"Moon Seok","family":"Lee","affiliation":"Department of Artificial Intelligence Convergence , Chonnam National University , Gwangju , Korea"},{"name":"Jae Hyun Yoon","slug":"jae-hyun-yoon","given":"Jae Hyun","family":"Yoon","affiliation":"Department of Artificial Intelligence Convergence , Chonnam National University , Gwangju , Korea"},{"name":"Seok Bong Yoo","slug":"seok-bong-yoo","given":"Seok Bong","family":"Yoo","affiliation":"Department of Artificial Intelligence Convergence , Chonnam National University , Gwangju , Korea"}],"abstract":"Adversarial attacks pose a severe threat to the accuracy of person re-identification (re-ID) systems, a critical security technology. Adversarial purification methods are promising approaches for defending against comprehensive attacks, including unseen ones. However, re-ID testing identities (IDs) are unseen, requiring more sophisticated purification than other classification tasks for adversarial defense. We propose IntensPure, an adversarial purification method in person re-ID that quantifies attack intensity via ID stability and attribute inconsistency to customize purification strength. Based on the estimated attack intensity, IntensPure employs secondary domain adaptive diffusion focused on purifying the low- and mid-frequency coefficients vulnerable to re-ID attacks. This method significantly reduces computational costs compared to the conventional diffusion method. For elaborate purification, IntensPure performs a directional diffusion process and refinements, leveraging the directional characteristics of secondary images. The experimental results on diverse attacks demonstrate that IntensPure outperforms the existing methods in terms of rank-1 accuracy.","doi":"10.24963/ijcai.2024/106","url":"https://ijcai.org/proceedings/2024/106","pdf":"https://ijcai.org/proceedings/2024/0106.pdf","markdown":"https://ijcai.org/proceedings/2024/106.md","bibtex":"https://ijcai.org/proceedings/2024/bibtex/106","volume":{"slug":"2024","title":"Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2024","url":"https://ijcai.org/proceedings/2024/","year":2024,"location":"Jeju, Korea","dates":"3-9 August 2024","editors":"Kate Larson","isbn":"978-1-956792-04-1","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2024"},"section":"Computer Vision","track":"Main Track","number":106,"pages":{"first":956,"last":964},"keywords":["Computer Vision: CV: Recognition (object detection, categorization)","Computer Vision: CV: Machine learning for vision","Computer Vision: CV: Adversarial learning, adversarial attack and defense methods"],"videos":[],"references":[{"position":1,"raw":"[Ankile et al., 2023] Lars Lien Ankile, Anna Midgley, and Sebastian Weisshaar. Denoising diffusion probabilistic models as a defense against adversarial attacks. arXiv :2301.06871, 2023.","title":"Denoising diffusion probabilistic models as a defense against adversarial attacks","authors":"Ankile","year":"2023","venue":null,"doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Bai et al., 2020] Song Bai, Yingwei Li, Yuyin Zhou, Qizhu Li, and Philip HS Torr. Adversarial metric attack and de- fense for person re-identification. IEEE Transactions on Pattern Analysis and Machine Intelligence, 43(6):2119- 2126, 2020.","title":"Adversarial metric attack and defense for person re-identification","authors":"Song Bai, Yingwei Li, Yuyin Zhou, Qizhu Li, Philip Hs Torr","year":"2020","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Bai et al., 2021] Tao Bai, Jinqi Luo, Jun Zhao, Bihan Wen, and Qian Wang. Recent advances in adversarial training for adversarial robustness. In IJCAI, 2021.","title":"Recent advances in adversarial training for adversarial robustness","authors":"Tao Bai, Jinqi Luo, Jun Zhao, Bihan Wen, Qian Wang","year":"2021","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2021/591"},{"position":4,"raw":"[Bouniot et al., 2020] Quentin Bouniot, Romaric Audigier, and Angelique Loesch. Vulnerability of person re- identification models to metric adversarial attacks. In CVPRW, 2020.","title":"Vulnerability of person reidentification models to metric adversarial attacks","authors":"Quentin Bouniot, Romaric Audigier, Angelique Loesch","year":"2020","venue":"CVPRW","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Carlini et al., 2023] Nicholas Carlini, Florian Tramer, Kr- ishnamurthy Dj Dvijotham, Leslie Rice, Mingjie Sun, and J Zico Kolter. (certified!!) adversarial robustness for free! In ICLR. 2023.","title":"certified!!) adversarial robustness for free!","authors":"Nicholas Carlini, Florian Tramer, Dj Krishnamurthy, Leslie Dvijotham, Mingjie Rice, J Zico Sun, Kolter","year":"2023","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Deng et al., 2021] Zhijie Deng, Xiao Yang, Shizhen Xu, Hang Su, and Jun Zhu. Libre: A practical bayesian ap- proach to adversarial detection. In CVPR, 2021.","title":"Libre: A practical bayesian approach to adversarial detection","authors":"Zhijie Deng, Xiao Yang, Shizhen Xu, Hang Su, Jun Zhu","year":"2021","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Du and Mordatch, 2019] Yilun Du and Igor Mordatch. Im- plicit generation and modeling with energy based models. NeurIPS, 32, 2019.","title":"Yilun Du and Igor Mordatch. Implicit generation and modeling with energy based models","authors":"Mordatch Du","year":"2019","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Feinman et al., 2017] Reuben Feinman, Ryan R Curtin, Saurabh Shintre, and Andrew B Gardner. Detecting adver- sarial samples from artifacts. arXiv :1703.00410, 2017.","title":"Detecting adversarial samples from artifacts","authors":"Reuben Feinman, Saurabh Ryan R Curtin, Andrew B Shintre, Gardner","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Gong et al., 2022] Yunpeng Gong, Liqing Huang, and Lifei Chen. Person re-identification method based on color at- tack and joint defence. In CVPR, 2022.","title":"Person re-identification method based on color attack and joint defence","authors":"Yunpeng Gong, Liqing Huang, Lifei Chen","year":"2022","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Gowal et al., 2020] Sven Gowal, Chongli Qin, Jonathan Uesato, Timothy Mann, and Pushmeet Kohli. Uncover- ing the limits of adversarial training against norm-bounded adversarial examples. arXiv :2010.03593, 2020.","title":"Uncovering the limits of adversarial training against norm-bounded adversarial examples","authors":"Sven Gowal, Chongli Qin, Jonathan Uesato, Timothy Mann, Pushmeet Kohli","year":"2020","venue":null,"doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Grathwohl et al., 2020] Will Grathwohl, Kuan-Chieh Wang, Jörn-Henrik Jacobsen, David Duvenaud, Moham- mad Norouzi, and Kevin Swersky. Your classifier is secretly an energy based model and you should treat it like one. ICLR, 2020.","title":"Your classifier is secretly an energy based model and you should treat it like one","authors":"Grathwohl","year":"2020","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[He et al., 2016] Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. Deep residual learning for image recog- nition. In CVPR, pages 770-778, 2016.","title":"Deep residual learning for image recognition","authors":"Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun","year":"2016","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Hendrycks and Gimpel, 2017] Dan Hendrycks and Kevin Gimpel. Early methods for detecting adversarial images. ICLR Workshop, 2017.","title":"Early methods for detecting adversarial images","authors":"Gimpel Hendrycks, Dan Hendrycks, Kevin Gimpel","year":"2017","venue":"ICLR Workshop","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Hill et al., 2021] Mitch Hill, Jonathan Mitchell, and Song- Chun Zhu. Stochastic security: Adversarial defense using long-run dynamics of energy-based models. ICLR, 2021.","title":"Stochastic security: Adversarial defense using long-run dynamics of energy-based models","authors":"Mitch Hill, Jonathan Mitchell, Song-Chun Zhu","year":"2021","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Kang et al., 2021] Qiyu Kang, Yang Song, Qinxu Ding, and Wee Peng Tay. Stable neural ode with lyapunov-stable equilibrium points for defending against adversarial at- tacks. NeurIPS, 2021.","title":"Stable neural ode with lyapunov-stable equilibrium points for defending against adversarial attacks","authors":"Kang","year":"2021","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Kang et al., 2023] Mintong Kang, Dawn Song, and Bo Li. Diffattack: Evasion attacks against diffusion-based adver- sarial purification. In NeurIPS, 2023.","title":"Diffattack: Evasion attacks against diffusion-based adversarial purification","authors":"Kang","year":"2023","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Kim et al., 2023] Hannah Kim, Celia Cintas, Gir- maw Abebe Tadesse, and Skyler Speakman. Spatially constrained adversarial attack detection and localization in the representation space of optical flow networks. In IJCAI, 2023.","title":"Spatially constrained adversarial attack detection and localization in the representation space of optical flow networks","authors":"Hannah Kim, Celia Cintas, Girmaw Abebe Tadesse, Skyler Speakman","year":"2023","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2023/107"},{"position":18,"raw":"[Lee and Kim, 2023] Minjong Lee and Dongwoo Kim. Ro- bust evaluation of diffusion-based adversarial purification. ICCV, 2023.","title":"Robust evaluation of diffusion-based adversarial purification","authors":"Lee, Kim ;, Minjong Lee, Dongwoo Kim","year":"2023","venue":"ICCV","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Li et al., 2019] Jie Li, Rongrong Ji, Hong Liu, Xiaopeng Hong, Yue Gao, and Qi Tian. Universal perturbation at- tack against image retrieval. In ICCV, pages 4899-4908, 2019.","title":"Universal perturbation attack against image retrieval","authors":"Jie Li, Rongrong Ji, Hong Liu, Xiaopeng Hong, Yue Gao, Qi Tian","year":"2019","venue":"ICCV","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Li et al., 2020] Shasha Li, Shitong Zhu, Sudipta Paul, Amit Roy-Chowdhury, Chengyu Song, Srikanth Krishnamurthy, Ananthram Swami, and Kevin S Chan. Connecting the dots: Detecting adversarial perturbations using context in- consistency. In ECCV, 2020.","title":"Connecting the dots: Detecting adversarial perturbations using context inconsistency","authors":"Shasha Li, Shitong Zhu, Sudipta Paul, Amit Roy-Chowdhury, Chengyu Song, Srikanth Krishnamurthy, Ananthram Swami, Kevin S Chan","year":"2020","venue":"ECCV","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Lin et al., 2019] Yutian Lin, Liang Zheng, Zhedong Zheng, Yu Wu, Zhilan Hu, Chenggang Yan, and Yi Yang. Im- proving person re-identification by attribute and identity learning. Pattern recognition, 95:151-161, 2019.","title":"Improving person re-identification by attribute and identity learning","authors":"Yutian Lin, Liang Zheng, Zhedong Zheng, Yu Wu, Zhilan Hu, Chenggang Yan, Yi Yang","year":"2019","venue":"Pattern recognition","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Liu et al., 2019] Jiayang Liu, Weiming Zhang, Yiwei Zhang, Dongdong Hou, Yujia Liu, Hongyue Zha, and Nenghai Yu. Detection based defense against adversarial examples from the steganalysis point of view. In CVPR, 2019.","title":"Detection based defense against adversarial examples from the steganalysis point of view","authors":"Jiayang Liu, Weiming Zhang, Yiwei Zhang, Dongdong Hou, Yujia Liu, Hongyue Zha, Nenghai Yu","year":"2019","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Liu et al., 2023] Han Liu, Xingshuo Huang, Xiaotong Zhang, Qimai Li, Fenglong Ma, Wei Wang, Hongyang Chen, Hong Yu, and Xianchao Zhang. Boosting decision- based black-box adversarial attack with gradient priors. In IJCAI, 2023.","title":"Boosting decisionbased black-box adversarial attack with gradient priors","authors":"Han Liu, Xingshuo Huang, Xiaotong Zhang, Qimai Li, Fenglong Ma, Wei Wang, Hongyang Chen, Hong Yu, Xianchao Zhang","year":"2023","venue":"IJCAI","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Lu et al., 2023] Zhuoran Lu, Zhuoyan Li, Chun-Wei Chi- ang, and Ming Yin. Strategic adversarial attacks in ai- assisted decision making to reduce human trust and re- liance. In IJCAI, 2023.","title":"Strategic adversarial attacks in aiassisted decision making to reduce human trust and reliance","authors":"Lu","year":"2023","venue":"IJCAI","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Madry et al., 2018] Aleksander Madry, Aleksandar Makelov, Ludwig Schmidt, Dimitris Tsipras, and Adrian Vladu. Towards deep learning models resistant to adversarial attacks. ICLR, 2018.","title":"Towards deep learning models resistant to adversarial attacks","authors":"Aleksander Madry, Aleksandar Makelov, Ludwig Schmidt, Dimitris Tsipras, Adrian Vladu","year":"2018","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Nie et al., 2022] Weili Nie, Brandon Guo, Yujia Huang, Chaowei Xiao, Arash Vahdat, and Anima Anandkumar. Diffusion models for adversarial purification. ICML, 2022.","title":"Diffusion models for adversarial purification","authors":"Weili Nie, Brandon Guo, Yujia Huang, Chaowei Xiao, Arash Vahdat, Anima Anandkumar","year":"2022","venue":null,"doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Ristani et al., 2016] Ergys Ristani, Francesco Solera, Roger Zou, Rita Cucchiara, and Carlo Tomasi. Performance mea- sures and a data set for multi-target, multi-camera track- ing. In ECCV, 2016.","title":"Performance measures and a data set for multi-target, multi-camera tracking","authors":"Ristani","year":"2016","venue":"ECCV","doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Saharia et al., 2022] Chitwan","title":"Chitwan","authors":"Saharia","year":"2022","venue":null,"doi":null,"url":null,"internal_url":null},{"position":29,"raw":"Saharia, William Chan, Hui- wen Chang, Chris Lee, Jonathan Ho, Tim Salimans, David Fleet, and Mohammad Norouzi. Palette: Image-to-image diffusion models. In ACM SIGGRAPH, pages 1-10, 2022.","title":"Palette: Image-to-image diffusion models","authors":"William Saharia, Huiwen Chan, Chris Chang, Jonathan Lee, Tim Ho, David Salimans, Mohammad Fleet, Norouzi","year":"2022","venue":"ACM SIGGRAPH","doi":null,"url":null,"internal_url":null},{"position":30,"raw":"[Samangouei et al., 2018] Pouya Samangouei, Maya Kabkab, and Rama Chellappa. Defense-gan: Protecting classifiers against adversarial attacks using generative models. ICLR, 2018.","title":"Defense-gan: Protecting classifiers against adversarial attacks using generative models","authors":"Pouya Samangouei, Maya Kabkab, Rama Chellappa","year":"2018","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":31,"raw":"[Shi et al., 2023] Yucheng Shi, Mengnan Du, Xuansheng Wu, Zihan Guan, Jin Sun, and Ninghao Liu. Black- box backdoor defense via zero-shot image purification. NeurIPS, 2023.","title":"Blackbox backdoor defense via zero-shot image purification","authors":"Yucheng Shi, Mengnan Du, Xuansheng Wu, Zihan Guan, Jin Sun, Ninghao Liu","year":"2023","venue":"NeurIPS","doi":null,"url":null,"internal_url":null},{"position":32,"raw":"[Song et al., 2018] Yang Song, Taesup Kim, Sebastian Nowozin, Stefano Ermon, and Nate Kushman. Pixelde- fend: Leveraging generative models to understand and de- fend against adversarial examples. ICLR, 2018.","title":"Pixeldefend: Leveraging generative models to understand and defend against adversarial examples","authors":"Yang Song, Taesup Kim, Sebastian Nowozin, Stefano Ermon, Nate Kushman","year":"2018","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":33,"raw":"[Sun et al., 2023] Jiachen Sun, Jiongxiao Wang, Weili Nie, Zhiding Yu, Zhuoqing Mao, and Chaowei Xiao. A critical revisit of adversarial robustness in 3D point cloud recog- nition with diffusion-driven purification. In ICML, 2023.","title":"A critical revisit of adversarial robustness in 3D point cloud recognition with diffusion-driven purification","authors":"Sun","year":"2023","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":34,"raw":"[Sun et al., 2024] Wenli Sun, Xinyang Jiang, Shuguang Dou, Dongsheng Li, Duoqian Miao, Cheng Deng, and Cairong Zhao. Invisible backdoor attack with dynamic triggers against person re-identification. IEEE Transactions on In- formation Forensics and Security, 19:307-319, 2024.","title":"Invisible backdoor attack with dynamic triggers against person re-identification","authors":"Wenli Sun, Xinyang Jiang, Shuguang Dou, Dongsheng Li, Duoqian Miao, Cheng Deng, Cairong Zhao","year":"2024","venue":"IEEE Transactions on Information Forensics and Security","doi":null,"url":null,"internal_url":null},{"position":35,"raw":"[Virtanen et al., 2020] Pauli Virtanen, Ralf Gommers, Travis E Oliphant, Matt Haberland, Tyler Reddy, David Cournapeau, Evgeni Burovski, Pearu Peterson, Warren Weckesser, Jonathan Bright, et al. Scipy 1.0: fundamental algorithms for scientific computing in python. Nature methods, 17(3):261-272, 2020.","title":"Scipy 1.0: fundamental algorithms for scientific computing in python","authors":"Pauli Virtanen, Ralf Gommers, Travis E Oliphant, Matt Haberland, Tyler Reddy, David Cournapeau, Evgeni Burovski, Pearu Peterson, Warren Weckesser, Jonathan Bright","year":"2020","venue":"Nature methods","doi":null,"url":null,"internal_url":null},{"position":36,"raw":"[Wang et al., 2020] Hongjun Wang, Guangrun Wang, Ya Li, Dongyu Zhang, and Liang Lin. Transferable, control- lable, and inconspicuous adversarial attacks on person re- identification with deep mis-ranking. In CVPR, 2020.","title":"Transferable, controllable, and inconspicuous adversarial attacks on person reidentification with deep mis-ranking","authors":"Hongjun Wang, Guangrun Wang, Ya Li, Dongyu Zhang, Liang Lin","year":"2020","venue":"CVPR","doi":null,"url":null,"internal_url":null},{"position":37,"raw":"[Wang et al., 2021a] Xueping Wang, Shasha Li, Min Liu, Yaonan Wang, and Amit K Roy-Chowdhury. Multi-expert adversarial attack detection in person re-identification us- ing context inconsistency. In ICCV, 2021.","title":"Multi-expert adversarial attack detection in person re-identification using context inconsistency","authors":"Wang","year":"2021","venue":"ICCV","doi":null,"url":null,"internal_url":null},{"position":38,"raw":"[Wang et al., 2021b] Yajie Wang, Shangbo Wu, Wenyi Jiang, Shengang Hao, Yu-an Tan, and Quanxin Zhang. Demiguise attack: Crafting invisible semantic adversarial perturbations with perceptual similarity. IJCAI, 2021.","title":"Demiguise attack: Crafting invisible semantic adversarial perturbations with perceptual similarity","authors":"Wang","year":"2021","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2021/430"},{"position":39,"raw":"[Wang et al., 2021c] Zeyuan Wang, Chaofeng Sha, and Su Yang. Reinforcement learning based sparse black-box adversarial attack on video recognition models. IJCAI, 2021.","title":"Reinforcement learning based sparse black-box adversarial attack on video recognition models","authors":"Wang","year":"2021","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2021/435"},{"position":40,"raw":"[Wang et al., 2022] Jinyi Wang, Zhaoyang Lyu, Dahua Lin, Bo Dai, and Hongfei Fu. Guided diffusion model for ad- versarial purification. ICML, 2022.","title":"Guided diffusion model for adversarial purification","authors":"Jinyi Wang, Zhaoyang Lyu, Dahua Lin, Bo Dai, Hongfei Fu","year":"2022","venue":null,"doi":null,"url":null,"internal_url":null},{"position":41,"raw":"[Wang et al., 2023] Qian Wang, Yongqin Xian, Hefei Ling, Jinyuan Zhang, Xiaorui Lin, Ping Li, Jiazhong Chen, and Ning Yu. Detecting adversarial faces using only real face self-perturbations. In IJCAI, 2023.","title":"Detecting adversarial faces using only real face self-perturbations","authors":"Qian Wang, Yongqin Xian, Hefei Ling, Jinyuan Zhang, Xiaorui Lin, Ping Li, Jiazhong Chen, Ning Yu","year":"2023","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2023/165"},{"position":42,"raw":"[Wu et al., 2022] Quanlin Wu, Hang Ye, and Yuntian Gu. Guided diffusion model for adversarial purification from random noise. arXiv :2206.10875, 2022.","title":"Guided diffusion model for adversarial purification from random noise","authors":"Wu","year":"2022","venue":null,"doi":null,"url":null,"internal_url":null},{"position":43,"raw":"[Xiao et al., 2023] Chaowei Xiao, Zhongzhu Chen, Kun Jin, Jiongxiao Wang, Weili Nie, Mingyan Liu, Anima Anand- kumar, Bo Li, and Dawn Song. Densepure: Understand- ing diffusion models for adversarial robustness. In ICLR, 2023.","title":"Densepure: Understanding diffusion models for adversarial robustness","authors":"Xiao","year":"2023","venue":"ICLR","doi":null,"url":null,"internal_url":null},{"position":44,"raw":"[Yang et al., 2022] Fengxiang Yang, Juanjuan Weng, Zhun Zhong, Hong Liu, Zheng Wang, Zhiming Luo, Donglin Cao, Shaozi Li, Shin'ichi Satoh, and Nicu Sebe. Towards robust person re-identification by defending against uni- versal attackers. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(4):5218-5235, 2022.","title":"Towards robust person re-identification by defending against universal attackers","authors":"Fengxiang Yang, Juanjuan Weng, Zhun Zhong, Hong Liu, Zheng Wang, Zhiming Luo, Donglin Cao, Shaozi Li, Shin'ichi Satoh, Nicu Sebe","year":"2022","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","doi":null,"url":null,"internal_url":null},{"position":45,"raw":"[Yang et al., 2024] Zhaoyuan Yang, Zhiwei Xu, Jing Zhang, Richard Hartley, and Peter Tu. Adversarial purification with the manifold hypothesis. In AAAI, 2024.","title":"Adversarial purification with the manifold hypothesis","authors":"Zhaoyuan Yang, Zhiwei Xu, Jing Zhang, Richard Hartley, Peter Tu","year":"2024","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":46,"raw":"[Yin et al., 2021] Mingjun Yin, Shasha Li, Zikui Cai, Chengyu Song, M Salman Asif, Amit K Roy-Chowdhury, and Srikanth V Krishnamurthy. Exploiting multi-object relationships for detecting adversarial attacks in complex scenes. In ICCV, 2021.","title":"Exploiting multi-object relationships for detecting adversarial attacks in complex scenes","authors":"Mingjun Yin, Shasha Li, Zikui Cai, Chengyu Song, Salman Asif, K Amit, Srikanth V Roy-Chowdhury, Krishnamurthy","year":"2021","venue":"ICCV","doi":null,"url":null,"internal_url":null},{"position":47,"raw":"[Yoon et al., 2021] Jongmin Yoon, Sung Ju Hwang, and Juho Lee. Adversarial purification with score-based gen- erative models. In ICML, 2021.","title":"Adversarial purification with score-based generative models","authors":"Jongmin Yoon, Sung Ju Hwang, Juho Lee","year":"2021","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":48,"raw":"[Yu et al., 2022] Chaojian Yu, Bo Han, Mingming Gong, Li Shen, Shiming Ge, Bo Du, and Tongliang Liu. Robust weight perturbation for adversarial training. IJCAI, 2022.","title":"Robust weight perturbation for adversarial training","authors":"Yu","year":"2022","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2022/512"},{"position":49,"raw":"[Zhang et al., 2023a] Jianping Zhang, Yung-Chieh Huang, Weibin Wu, and Michael R Lyu. Towards semantics-and domain-aware adversarial attacks. In IJCAI, 2023.","title":"Towards semantics-and domain-aware adversarial attacks","authors":"Zhang","year":"2023","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2023/60"},{"position":50,"raw":"[Zhang et al., 2023b] Shuhai Zhang, Feng Liu, Jiahao Yang, Yifan Yang, Changsheng Li, Bo Han, and Mingkui Tan. Detecting adversarial data by probing multiple perturba- tions using expected perturbation score. In ICML, 2023.","title":"Detecting adversarial data by probing multiple perturbations using expected perturbation score","authors":"Zhang","year":"2023","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":51,"raw":"[Zheng et al., 2015] Liang Zheng, Liyue Shen, Lu Tian, Shengjin Wang, Jingdong Wang, and Qi Tian. Scalable person re-identification: A benchmark. In ICCV, 2015.","title":"Scalable person re-identification: A benchmark","authors":"Liang Zheng, Liyue Shen, Lu Tian, Shengjin Wang, Jingdong Wang, Qi Tian","year":"2015","venue":"ICCV","doi":null,"url":null,"internal_url":null},{"position":52,"raw":"[Zheng et al., 2016] Liang Zheng, Yi Yang, and Alexander G Hauptmann. Person re-identification: Past, present and future. arXiv :1610.02984, 2016.","title":"Person re-identification: Past, present and future","authors":"Liang Zheng, Yi Yang, Alexander G Hauptmann","year":"2016","venue":null,"doi":null,"url":null,"internal_url":null},{"position":53,"raw":"[Zheng et al., 2018a] Zhedong Zheng, Liang Zheng, Zhilan Hu, and Yi Yang. Open set adversarial examples. arXiv :1809.02681, 3, 2018.","title":"Open set adversarial examples","authors":"Zheng","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":54,"raw":"[Zheng et al., 2018b] Zhedong Zheng, Liang Zheng, and Yi Yang. A discriminatively learned cnn embedding for person reidentification. ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM), 14(1):13, 2018.","title":"A discriminatively learned cnn embedding for person reidentification","authors":"Zheng","year":"2018","venue":"ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM)","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}