{"type":"ScholarlyArticle","title":"PRASS: Probabilistic Risk-averse Robust Learning with Stochastic Search","authors":[{"name":"Tianle Zhang","slug":"tianle-zhang","given":"Tianle","family":"Zhang","affiliation":"Department of Computer Science , University of Liverpool , Liverpool , L69 3BX , UK"},{"name":"Yanghao Zhang","slug":"yanghao-zhang","given":"Yanghao","family":"Zhang","affiliation":"Department of Computer Science , University of Liverpool , Liverpool , L69 3BX , UK"},{"name":"Ronghui Mu","slug":"ronghui-mu","given":"Ronghui","family":"Mu","affiliation":"Department of Computer Science , University of Liverpool , Liverpool , L69 3BX , UK"},{"name":"Jiaxu Liu","slug":"jiaxu-liu","given":"Jiaxu","family":"Liu","affiliation":"Department of Computer Science , University of Liverpool , Liverpool , L69 3BX , UK"},{"name":"Jonathan Fieldsend","slug":"jonathan-fieldsend","given":"Jonathan","family":"Fieldsend","affiliation":"Department of Computer Science , University of Exeter , Exeter , EX4 4QF , UK"},{"name":"Wenjie Ruan","slug":"wenjie-ruan","given":"Wenjie","family":"Ruan","affiliation":"Department of Computer Science , University of Liverpool , Liverpool , L69 3BX , UK"}],"abstract":"Deep learning models, despite their remarkable success in various tasks, have been shown to be vulnerable to adversarial perturbations. Although robust learning techniques that consider adversarial risks against worst-case perturbations can effectively increase a model's robustness, they may not always be the most suitable approach. This is due to the fact that in certain scenarios, perturbations are more likely to occur probabilistically rather than being intentionally crafted by attackers.\r\nTo address this challenge, we propose a novel risk-averse robust learning method based on entropic value-at-risk, called PRASS (Probabilistical Risk-Averse Robust Learning with Stochastic Search). Our approach leverages principles of stochastic optimisation and considers perturbing distributions rather than solely worst-case adversaries. By applying adaptive stochastic search to parameterised distributions, we further enhance the scalability of PRASS to handle distributional robustness. Empirical experiments demonstrate that PRASS outperforms existing state-of-the-art baselines.","doi":"10.24963/ijcai.2024/62","url":"https://ijcai.org/proceedings/2024/62","pdf":"https://ijcai.org/proceedings/2024/0062.pdf","markdown":"https://ijcai.org/proceedings/2024/62.md","bibtex":"https://ijcai.org/proceedings/2024/bibtex/62","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":"AI Ethics, Trust, Fairness","track":"Main Track","number":62,"pages":{"first":559,"last":567},"keywords":["Machine Learning: ML: Adversarial machine learning","Machine Learning: ML: Robustness","AI Ethics, Trust, Fairness: ETF: Trustworthy AI","AI Ethics, Trust, Fairness: ETF: Safety and robustness"],"videos":[],"references":[{"position":1,"raw":"[Ahmadi et al., 2022] Mohamadreza Ahmadi, Xiaobin Xiong, and Aaron D. Ames. Risk-averse control via cvar barrier functions: Application to bipedal robot locomotion. IEEE Control Systems Letters, 6:878-883, 2022.","title":"Risk-averse control via cvar barrier functions: Application to bipedal robot locomotion","authors":"Ahmadi","year":"2022","venue":"IEEE Control Systems Letters","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Awasthi et al., 2020] Pranjal Awasthi, Himanshu Jain, Ankit Singh Rawat, and Aravindan Vijayaraghavan. Ad- versarial robustness via robust low rank representations. In Proceedings of the 34th Conference on Neural Informa- tion Processing Systems, volume 33, pages 11391-11403, 2020.","title":"Adversarial robustness via robust low rank representations","authors":"Pranjal Awasthi, Himanshu Jain, Ankit Singh Rawat, Aravindan Vijayaraghavan","year":"2020","venue":"Proceedings of the 34th Conference on Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Balunovic and Vechev, 2020] Mislav Balunovic and Mar- tin T. Vechev. Adversarial training and provable defenses: Bridging the gap. In Proceedings of the 8th International Conference on Learning Representations, 2020.","title":"Mislav Balunovic and Martin T. Vechev. Adversarial training and provable defenses: Bridging the gap","authors":"Vechev Balunovic","year":"2020","venue":"Proceedings of the 8th International Conference on Learning Representations","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Bartlett et al., 2017] Peter L. Bartlett, Dylan J. Foster, and Matus Telgarsky. Spectrally-normalized margin bounds for neural networks. In Proceedings of the 31st Conference on Neural Information Processing Systems, pages 6240- 6249, 2017.","title":"Spectrally-normalized margin bounds for neural networks","authors":"L Peter, Dylan J Bartlett, Matus Foster, Telgarsky","year":"2017","venue":"Proceedings of the 31st Conference on Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Cohen et al., 2019] Jeremy M. Cohen, Elan Rosenfeld, and J. Zico Kolter. Certified adversarial robustness via ran- domized smoothing. In Proceedings of the 36th Interna- tional Conference on Machine Learning, volume 97, pages 1310-1320, 2019.","title":"Certified adversarial robustness via randomized smoothing","authors":"Jeremy M Cohen, Elan Rosenfeld, J Zico Kolter","year":"2019","venue":"Proceedings of the 36th International Conference on Machine Learning","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Croce and Hein, 2020] Francesco Croce and Matthias Hein. Provable robustness against all adversarial $l p$- perturbations for $p\\geq 1$. In Proceedings of the 8th International Conference on Learning Representations, 2020.","title":"Francesco Croce and Matthias Hein. Provable robustness against all adversarial $l p$perturbations for $p\\geq 1$","authors":"Hein Croce","year":"2020","venue":"Proceedings of the 8th International Conference on Learning Representations","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Croce et al., 2019] Francesco Croce, Maksym An- driushchenko, and Matthias Hein. Provable robustness of relu networks via maximization of linear regions. In Proceedings of the 22nd International Conference on Artificial Intelligence and Statistics, volume 89, pages 2057-2066, 2019.","title":"Provable robustness of relu networks via maximization of linear regions","authors":"Francesco Croce, Maksym Andriushchenko, Matthias Hein","year":"2019","venue":"Proceedings of the 22nd International Conference on Artificial Intelligence and Statistics","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Dong et al., 2020] Yinpeng Dong, Zhijie Deng, Tianyu Pang, Jun Zhu, and Hang Su. Proceedings of the 34th con- ference on neural information processing systems. In Ad- vances in Neural Information Processing Systems, pages 8270-8283, 2020.","title":"Proceedings of the 34th conference on neural information processing systems","authors":"Dong","year":"2020","venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Fan and Li, 2021] Jiameng Fan and Wenchao Li. Adversar- ial training and provable robustness: A tale of two objec- tives. In Proceedings of the 35th AAAI Conference on Ar- tificial Intelligence, volume 35, pages 7367-7376, 2021.","title":"Jiameng Fan and Wenchao Li. Adversarial training and provable robustness: A tale of two objectives","authors":"Fan, Li","year":"2021","venue":"Proceedings of the 35th AAAI Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Gowal et al., 2019] Sven Gowal, Krishnamurthy Dvi- jotham, Robert Stanforth, Rudy Bunel, Chongli Qin, Jonathan Uesato, Relja Arandjelovic, Timothy Arthur Mann, and Pushmeet Kohli. Scalable verified training for provably robust image classification. In Proceedings of IEEE/CVF International Conference on Computer Vision, pages 4841-4850, 2019.","title":"Scalable verified training for provably robust image classification","authors":"Sven Gowal, Krishnamurthy Dvijotham, Robert Stanforth, Rudy Bunel, Chongli Qin, Jonathan Uesato, Relja Arandjelovic, Timothy Arthur Mann, Pushmeet Kohli","year":"2019","venue":"Proceedings of IEEE/CVF International Conference on Computer Vision","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Huang et al., 2017] Xiaowei Huang, Marta Kwiatkowska, Sen Wang, and Min Wu. Safety verification of deep neural networks. In Proceedings of the 29th International Con- ference on Computer Aided Verification, volume 10426, pages 3-29. Springer, 2017.","title":"Safety verification of deep neural networks","authors":"Xiaowei Huang, Marta Kwiatkowska, Sen Wang, Min Wu","year":"2017","venue":"Proceedings of the 29th International Conference on Computer Aided Verification","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Huang et al., 2020] Xiaowei Huang, Daniel Kroening, Wenjie Ruan, James Sharp, Youcheng Sun, Emese Thamo, Min Wu, and Xinping Yi. A survey of safety and trust- worthiness of deep neural networks: Verification, testing, adversarial attack and defence, and interpretability. Com- puter Science Review, 37:100270, 2020.","title":"A survey of safety and trustworthiness of deep neural networks: Verification, testing, adversarial attack and defence, and interpretability","authors":"Xiaowei Huang, Daniel Kroening, Wenjie Ruan, James Sharp, Youcheng Sun, Emese Thamo, Min Wu, Xinping Yi","year":"2020","venue":"Computer Science Review","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[ISO, 2014] IEC ISO. Iso/iec guide 51: Safety aspects- guidelines for their inclusion in standards. Geneva, Switzerland, 2014.","title":"IEC ISO. Iso/iec guide 51: Safety aspectsguidelines for their inclusion in standards","authors":null,"year":"2014","venue":null,"doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Jin et al., 2022] Gaojie Jin, Xinping Yi, Wei Huang, Sven Schewe, and Xiaowei Huang. Enhancing adversarial train- ing with second-order statistics of weights. In Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 15252-15262, 2022.","title":"Enhancing adversarial training with second-order statistics of weights","authors":"Jin","year":"2022","venue":"Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Lécuyer et al., 2019] Mathias Lécuyer, Vaggelis Atlidakis, Roxana Geambasu, Daniel Hsu, and Suman Jana. Certi- fied robustness to adversarial examples with differential privacy. In IEEE Symposium on Security and Privacy, pages 656-672, 2019.","title":"Certified robustness to adversarial examples with differential privacy","authors":"Mathias Lécuyer, Vaggelis Atlidakis, Roxana Geambasu, Daniel Hsu, Suman Jana","year":"2019","venue":"IEEE Symposium on Security and Privacy","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Li et al., 2023] Tian Li, Ahmad Beirami, Maziar Sanjabi, and Virginia Smith. On tilted losses in machine learning: Theory and applications. Journal of Machine Learning Research, 24:142:1-142:79, 2023.","title":"On tilted losses in machine learning: Theory and applications","authors":"Tian Li, Ahmad Beirami, Maziar Sanjabi, Virginia Smith","year":"2023","venue":"Journal of Machine Learning Research","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Lyu et al., 2021] Zhaoyang Lyu, Minghao Guo, Tong Wu, Guodong Xu, Kehuan Zhang, and Dahua Lin. Towards evaluating and training verifiably robust neural networks. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pages 4308-4317, 2021.","title":"Towards evaluating and training verifiably robust neural networks","authors":"Zhaoyang Lyu, Minghao Guo, Tong Wu, Guodong Xu, Kehuan Zhang, Dahua Lin","year":"2021","venue":"Proceedings of IEEE Conference on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Madry et al., 2018] Aleksander Madry, Aleksandar Makelov, Ludwig Schmidt, Dimitris Tsipras, and Adrian Vladu. Towards deep learning models resistant to adversarial attacks. In Proceedings of the 6th International Conference on Learning Representations, 2018.","title":"Towards deep learning models resistant to adversarial attacks","authors":"Aleksander Madry, Aleksandar Makelov, Ludwig Schmidt, Dimitris Tsipras, Adrian Vladu","year":"2018","venue":"Proceedings of the 6th International Conference on Learning Representations","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Majumdar and Pavone, 2017] Anirudha Majumdar and Marco Pavone. How should a robot assess risk? towards an axiomatic theory of risk in robotics. In Proceedings of the 18th International Symposium on Robotics Research, volume 10, pages 75-84, 2017.","title":"How should a robot assess risk? towards an axiomatic theory of risk in robotics","authors":"Anirudha Majumdar, Marco Pavone","year":"2017","venue":"Proceedings of the 18th International Symposium on Robotics Research","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Mirman et al., 2018] Matthew Mirman, Timon Gehr, and Martin T. Vechev. Differentiable abstract interpretation for provably robust neural networks. In Proceedings of the 35th International Conference on Machine Learning, volume 80, pages 3575-3583, 2018.","title":"Differentiable abstract interpretation for provably robust neural networks","authors":"Matthew Mirman, Timon Gehr, Martin T Vechev","year":"2018","venue":"Proceedings of the 35th International Conference on Machine Learning","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Mohri and Rostamizadeh, 2008] Mehryar Mohri and Af- shin Rostamizadeh. Rademacher complexity bounds for non-i.i.d. processes. In Proceedings of Conference on Neu- ral Information Processing Systems, pages 1097-1104, 2008.","title":"Rademacher complexity bounds for non-i.i.d. processes","authors":"Mehryar Mohri, Afshin Rostamizadeh","year":"2008","venue":"Proceedings of Conference on Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Mohri et al., 2018] Mehryar Mohri, Afshin Rostamizadeh, and Ameet Talwalkar. Foundations of Machine Learning. Adaptive computation and machine learning. 2018.","title":"Foundations of Machine Learning. Adaptive computation and machine learning","authors":"Mehryar Mohri, Afshin Rostamizadeh, Ameet Talwalkar","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Mu et al., 2021] Ronghui Mu, Wenjie Ruan, Leandro Sori- ano Marcolino, and Qiang Ni. Sparse adversarial video attacks with spatial transformations. In Proceedings of the 32nd British Machine Vision Conference, page 101, 2021.","title":"Sparse adversarial video attacks with spatial transformations","authors":"Mu","year":"2021","venue":"Proceedings of the 32nd British Machine Vision Conference","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Ollivier et al., 2017] Yann Ollivier, Ludovic Arnold, Anne Auger, and Nikolaus Hansen. Information-geometric optimization algorithms: A unifying picture via invari- ance principles. Journal of Machine Learning Research, 18:18:1-18:65, 2017.","title":"Information-geometric optimization algorithms: A unifying picture via invariance principles","authors":"Yann Ollivier, Ludovic Arnold, Anne Auger, Nikolaus Hansen","year":"2017","venue":"Journal of Machine Learning Research","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Robey et al., 2021] Alexander Robey, Luiz F. O. Cha- mon, George J. Pappas, Hamed Hassani, and Alejandro Ribeiro. Adversarial robustness with semi-infinite con- strained learning. In Proceedings of the 35th Conference on Neural Information Processing Systems, pages 6198- 6215, 2021.","title":"Adversarial robustness with semi-infinite constrained learning","authors":"Alexander Robey, F O Luiz, George J Chamon, Hamed Pappas, Alejandro Hassani, Ribeiro","year":"2021","venue":"Proceedings of the 35th Conference on Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Robey et al., 2022] Alexander Robey, Luiz F. O. Chamon, George J. Pappas, and Hamed Hassani. Probabilistically robust learning: Balancing average and worst-case per- formance. In Proceedings of International Conference on Machine Learning, volume 162, pages 18667-18686, 2022.","title":"Probabilistically robust learning: Balancing average and worst-case performance","authors":"Alexander Robey, F O Luiz, George J Chamon, Hamed Pappas, Hassani","year":"2022","venue":"Proceedings of International Conference on Machine Learning","doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Rockafellar et al., 2000] R Tyrrell Rockafellar, Stanislav Uryasev, et al. Optimization of conditional value-at-risk. Journal of risk, 2000.","title":"Optimization of conditional value-at-risk","authors":"Stanislav Tyrrell Rockafellar, Uryasev","year":"2000","venue":"Journal of risk","doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Salman et al., 2019] Hadi Salman, Jerry Li, Ilya P. Razen- shteyn, Pengchuan Zhang, Huan Zhang, Sébastien Bubeck, and Greg Yang. Provably robust deep learning via adversarially trained smoothed classifiers. In Proceedings of the 33rd Conference on Neural Information Processing Systems, pages 11289-11300, 2019.","title":"Provably robust deep learning via adversarially trained smoothed classifiers","authors":"Jerry Hadi Salman, Ilya P Li, Pengchuan Razenshteyn, Huan Zhang, Sébastien Zhang, Greg Bubeck, Yang","year":"2019","venue":"Proceedings of the 33rd Conference on Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":29,"raw":"[Schmidt et al., 2018] Ludwig Schmidt, Shibani Santurkar, Dimitris Tsipras, Kunal Talwar, and Aleksander Madry. Adversarially robust generalization requires more data. In Proceedings of the 32nd Conference on Neural Informa- tion Processing Systems, pages 5019-5031, 2018.","title":"Adversarially robust generalization requires more data","authors":"Schmidt","year":"2018","venue":"Proceedings of the 32nd Conference on Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":30,"raw":"[Shalev-Shwartz and Ben-David, 2014] Shai Shalev- Shwartz and Shai Ben-David. Understanding Machine Learning -From Theory to Algorithms. Cambridge University Press, 2014.","title":"Understanding Machine Learning -From Theory to Algorithms","authors":"Shai Shalev, -Shwartz, Shai Ben-David","year":"2014","venue":null,"doi":null,"url":null,"internal_url":null},{"position":31,"raw":"[Shi et al., 2021] Zhouxing Shi, Yihan Wang, Huan Zhang, Jinfeng Yi, and Cho-Jui Hsieh. Fast certified robust train- ing via better initialization and shorter warmup. CoRR, 2021.","title":"Fast certified robust training via better initialization and shorter warmup","authors":"Zhouxing Shi, Yihan Wang, Huan Zhang, Jinfeng Yi, Cho-Jui Hsieh","year":"2021","venue":"CoRR","doi":null,"url":null,"internal_url":null},{"position":32,"raw":"[Tjeng et al., 2019] Vincent Tjeng, Kai Yuanqing Xiao, and Russ Tedrake. Evaluating robustness of neural networks with mixed integer programming. In Proceedings of the 7th International Conference on Learning Representa- tions, 2019.","title":"Evaluating robustness of neural networks with mixed integer programming","authors":"Vincent Tjeng, Kai Yuanqing, Xiao, Russ Tedrake","year":"2019","venue":"Proceedings of the 7th International Conference on Learning Representations","doi":null,"url":null,"internal_url":null},{"position":33,"raw":"[Wang et al., 2021] Fu Wang, Yanghao Zhang, Yanbin Zheng, and Wenjie Ruan. Gradient-guided dynamic ef- ficient adversarial training. CoRR, 2021.","title":"Gradient-guided dynamic efficient adversarial training","authors":"Fu Wang, Yanghao Zhang, Yanbin Zheng, Wenjie Ruan","year":"2021","venue":"CoRR","doi":null,"url":null,"internal_url":null},{"position":34,"raw":"[Wong et al., 2020] Eric Wong, Leslie Rice, and J. Zico Kolter. Fast is better than free: Revisiting adversarial train- ing. In Proceedings of the 8th International Conference on Learning Representations, 2020.","title":"Fast is better than free: Revisiting adversarial training","authors":"Eric Wong, Leslie Rice, J Zico Kolter","year":"2020","venue":"Proceedings of the 8th International Conference on Learning Representations","doi":null,"url":null,"internal_url":null},{"position":35,"raw":"[Yin et al., 2019] Dong Yin, Kannan Ramchandran, and Pe- ter L. Bartlett. Rademacher complexity for adversarially robust generalization. In Proceedings of the 36th Interna- tional Conference on Machine Learning, volume 97, pages 7085-7094, 2019.","title":"Rademacher complexity for adversarially robust generalization","authors":"Yin","year":"2019","venue":"Proceedings of the 36th International Conference on Machine Learning","doi":null,"url":null,"internal_url":null},{"position":36,"raw":"[Zhai et al., 2020] Runtian Zhai, Chen Dan, Di He, Huan Zhang, Boqing Gong, Pradeep Ravikumar, Cho-Jui Hsieh, and Liwei Wang. MACER: attack-free and scalable robust training via maximizing certified radius. In Proceedings of the 8th International Conference on Learning Representa- tions, 2020.","title":"MACER: attack-free and scalable robust training via maximizing certified radius","authors":"Runtian Zhai, Chen Dan, Di He, Huan Zhang, Boqing Gong, Pradeep Ravikumar, Cho-Jui Hsieh, Liwei Wang","year":"2020","venue":"Proceedings of the 8th International Conference on Learning Representations","doi":null,"url":null,"internal_url":null},{"position":37,"raw":"[Zhang et al., 2019] Hongyang Zhang, Yaodong Yu, Jiantao Jiao, Eric P. Xing, Laurent El Ghaoui, and Michael I. Jor- dan. Theoretically principled trade-off between robust- ness and accuracy. In Proceedings of the 36th Interna- tional Conference on Machine Learning, volume 97, pages 7472-7482, 2019.","title":"Theoretically principled trade-off between robustness and accuracy","authors":"Hongyang Zhang, Yaodong Yu, Jiantao Jiao, Eric P Xing, Laurent El Ghaoui, Michael I Jordan","year":"2019","venue":"Proceedings of the 36th International Conference on Machine Learning","doi":null,"url":null,"internal_url":null},{"position":38,"raw":"[Zhang et al., 2020a] Huan Zhang, Hongge Chen, Chaowei Xiao, Sven Gowal, Robert Stanforth, Bo Li, Duane S. Boning, and Cho-Jui Hsieh. Towards stable and efficient training of verifiably robust neural networks. In Proceed- ings of the 8th International Conference on Learning Rep- resentations, 2020.","title":"Towards stable and efficient training of verifiably robust neural networks","authors":"Zhang","year":"2020","venue":"Proceedings of the 8th International Conference on Learning Representations","doi":null,"url":null,"internal_url":null},{"position":39,"raw":"[Zhang et al., 2020b] Tianle Zhang, Muzhou Hou, Tao Zhou, Zhaode Liu, Weirong Cheng, and Yangjin Cheng. Land-use classification via ensemble dropout information discriminative extreme learning machine based on deep convolution feature. Computer Science and Information Systems, 17(2):427-443, 2020.","title":"Land-use classification via ensemble dropout information discriminative extreme learning machine based on deep convolution feature","authors":"Zhang","year":"2020","venue":"Computer Science and Information Systems","doi":null,"url":null,"internal_url":null},{"position":40,"raw":"[Zhang et al., 2021] Bohang Zhang, Tianle Cai, Zhou Lu, Di He, and Liwei Wang. Towards certifying l-infinity ro- bustness using neural networks with l-inf-dist neurons. In Proceedings of the 38th International Conference on Ma- chine Learning, volume 139, pages 12368-12379, 2021.","title":"Towards certifying l-infinity robustness using neural networks with l-inf-dist neurons","authors":"Zhang","year":"2021","venue":"Proceedings of the 38th International Conference on Machine Learning","doi":null,"url":null,"internal_url":null},{"position":41,"raw":"[Zhang et al., 2022] Tianle Zhang, Wenjie Ruan, and Jonathan E. Fieldsend. Proa: A probabilistic robustness assessment against functional perturbations. In Proceed- ings of Machine Learning and Knowledge Discovery in Databases -European Conference, volume 13715, pages 154-170, 2022.","title":"Proa: A probabilistic robustness assessment against functional perturbations","authors":"Zhang","year":"2022","venue":"Proceedings of Machine Learning and Knowledge Discovery in Databases -European Conference","doi":null,"url":null,"internal_url":null},{"position":42,"raw":"[Zhou and Hu, 2014] Enlu Zhou and Jiaqiao Hu. Gradient- based adaptive stochastic search for non-differentiable op- timization. IEEE Transactions on Automatic Control, 59(7):1818-1832, 2014.","title":"Gradientbased adaptive stochastic search for non-differentiable optimization","authors":"Hu Zhou, Enlu Zhou, Jiaqiao Hu","year":"2014","venue":"IEEE Transactions on Automatic Control","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}