{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T16:03:29Z","timestamp":1780589009617,"version":"3.54.1"},"publisher-location":"New York, NY, USA","reference-count":35,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1145\/3779208.3805970","type":"proceedings-article","created":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T15:21:58Z","timestamp":1780586518000},"page":"1770-1785","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["From Curvature to Privacy: EER-Driven Differential Privacy in Deep Neural Networks"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2713-6277","authenticated-orcid":false,"given":"Islam","family":"Monir","sequence":"first","affiliation":[{"name":"College of Science and Engineering, Hamad Bin Khalifa University, Doha, Qatar"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8372-3006","authenticated-orcid":false,"given":"Gabriel","family":"Ghinita","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Massachusetts Boston, Boston, Massachusetts, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3261-7588","authenticated-orcid":false,"given":"Mohamed","family":"Abdallah","sequence":"additional","affiliation":[{"name":"College of Science and Engineering, Hamad Bin Khalifa University, Doha, Qatar"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,6,4]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/2976749.2978318"},{"key":"e_1_3_2_1_2_1","first-page":"17455","article-title":"Differentially private learning with adaptive clipping","volume":"34","author":"Andrew Galen","year":"2021","unstructured":"Galen Andrew, Om Thakkar, Brendan McMahan, and Swaroop Ramaswamy. 2021. Differentially private learning with adaptive clipping. Advances in Neural Information Processing Systems 34 (2021), 17455\u201317466.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_3_1","volume-title":"Have it your way: Individualized Privacy Assignment for DP-SGD. Advances in Neural Information Processing Systems 36","author":"Boenisch Franziska","year":"2024","unstructured":"Franziska Boenisch, Christopher M\u00fchl, Adam Dziedzic, Roy Rinberg, and Nicolas Papernot. 2024. Have it your way: Individualized Privacy Assignment for DP-SGD. Advances in Neural Information Processing Systems 36 (2024)."},{"key":"e_1_3_2_1_4_1","volume-title":"Convex optimization","author":"Boyd Stephen","unstructured":"Stephen Boyd and Lieven Vandenberghe. 2004. Convex optimization. Cambridge university press."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/BigData50022.2020.9378011"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2023.3293961"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1007\/11787006_1"},{"key":"e_1_3_2_1_8_1","volume-title":"Adaptive Hyperparameter Selection for Differentially Private Gradient Descent. Transactions on Machine Learning Research","author":"Fay Dominik","year":"2023","unstructured":"Dominik Fay, Sindri Magn\u00fasson, Jens Sj\u00f6lund, and Mikael Johansson. 2023. Adaptive Hyperparameter Selection for Differentially Private Gradient Descent. Transactions on Machine Learning Research (2023)."},{"key":"e_1_3_2_1_9_1","volume-title":"Nonlinear and mixed-integer optimization: fundamentals and applications","author":"Floudas Christodoulos A","unstructured":"Christodoulos A Floudas. 1995. Nonlinear and mixed-integer optimization: fundamentals and applications. Oxford University Press."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/TrustCom56396.2022.00094"},{"key":"e_1_3_2_1_11_1","volume-title":"moments and quadrature with applications","author":"Golub Gene H","unstructured":"Gene H Golub and G\u00e9rard Meurant. 2009. Matrices, moments and quadrature with applications. Princeton University Press."},{"key":"e_1_3_2_1_12_1","volume-title":"A survey on differentially private machine learning","author":"Gong Maoguo","year":"2020","unstructured":"Maoguo Gong, Yu Xie, Ke Pan, Kaiyuan Feng, and Alex Kai Qin. 2020. A survey on differentially private machine learning. IEEE computational intelligence magazine (2020), 49\u201364."},{"key":"e_1_3_2_1_13_1","volume-title":"Arturs Backurs, Nenghai Yu, and Jiang Bian.","author":"He Jiyan","year":"2022","unstructured":"Jiyan He, Xuechen Li, Da Yu, Huishuai Zhang, Janardhan Kulkarni, Yin Tat Lee, Arturs Backurs, Nenghai Yu, and Jiang Bian. 2022. Exploring the limits of differentially private deep learning with group-wise clipping. arXiv preprint arXiv:2212.01539 (2022)."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3531146.3533070"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-16-8193-6_4"},{"key":"e_1_3_2_1_16_1","volume-title":"International Conference on Artificial Intelligence and Statistics. 2465\u20132475","author":"Koskela Antti","year":"2020","unstructured":"Antti Koskela and Antti Honkela. 2020. Learning rate adaptation for differentially private learning. In International Conference on Artificial Intelligence and Statistics. 2465\u20132475."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3220076"},{"key":"e_1_3_2_1_18_1","volume-title":"Fine-tuning language models with differential privacy through adaptive noise allocation. arXiv preprint arXiv:2410.02912","author":"Li Xianzhi","year":"2024","unstructured":"Xianzhi Li, Ran Zmigrod, Zhiqiang Ma, Xiaomo Liu, and Xiaodan Zhu. 2024. Fine-tuning language models with differential privacy through adaptive noise allocation. arXiv preprint arXiv:2410.02912 (2024)."},{"key":"e_1_3_2_1_19_1","series-title":"SIAM review 58, 1","volume-title":"Approximating spectral densities of large matrices","author":"Lin Lin","year":"2016","unstructured":"Lin Lin, Yousef Saad, and Chao Yang. 2016. Approximating spectral densities of large matrices. SIAM review 58, 1 (2016), 34\u201365."},{"key":"e_1_3_2_1_20_1","volume-title":"R\u00e9nyi Differential Privacy. In 2017 IEEE 30th Computer Security Foundations Symposium (CSF). 263\u2013275","author":"Mironov Ilya","year":"2017","unstructured":"Ilya Mironov. 2017. R\u00e9nyi Differential Privacy. In 2017 IEEE 30th Computer Security Foundations Symposium (CSF). 263\u2013275."},{"key":"e_1_3_2_1_21_1","volume-title":"DaWaK 2024, Naples, Italy, August 26-28, 2024, Proceedings (Lecture Notes in Computer Science","volume":"222","author":"Islam","unstructured":"Islam A. Monir and Gabriel Ghinita. 2024. Differentially-Private Neural Network Training with Private Features and Public Labels. In Big Data Analytics and Knowledge Discovery - 26th International Conference, DaWaK 2024, Naples, Italy, August 26-28, 2024, Proceedings (Lecture Notes in Computer Science, Vol. 14912). Springer, 208\u2013222."},{"key":"e_1_3_2_1_22_1","volume-title":"Felix X Yu, Sashank J Reddi, and Sanjiv Kumar.","author":"Pichapati Venkatadheeraj","year":"2019","unstructured":"Venkatadheeraj Pichapati, Ananda Theertha Suresh, Felix X Yu, Sashank J Reddi, and Sanjiv Kumar. 2019. Adaclip: Adaptive clipping for private sgd. arXiv preprint arXiv: 1908.07643 (2019)."},{"key":"e_1_3_2_1_23_1","volume-title":"Differentially Private Active Learning: Balancing Effective Data Selection and Privacy. In 2025 IEEE Conference on Secure and Trustworthy Machine Learning (SaTML). IEEE, 858\u2013878","author":"Schwethelm Kristian","year":"2025","unstructured":"Kristian Schwethelm, Johannes Kaiser, Jonas Kuntzer, Mehmet Yigitsoy, Daniel R\u00fcckert, and Georgios Kaissis. 2025. Differentially Private Active Learning: Balancing Effective Data Selection and Privacy. In 2025 IEEE Conference on Secure and Trustworthy Machine Learning (SaTML). IEEE, 858\u2013878."},{"key":"e_1_3_2_1_24_1","volume-title":"Membership Inference Attacks Against Machine Learning Models. IEEE Symposium on Security and Privacy (SP)","author":"Shokri R.","year":"2016","unstructured":"R. Shokri, Marco Stronati, Congzheng Song, and Vitaly Shmatikov. 2016. Membership Inference Attacks Against Machine Learning Models. IEEE Symposium on Security and Privacy (SP) (2016), 3\u201318."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1137\/16M1104974"},{"key":"e_1_3_2_1_26_1","unstructured":"Koen Lennart van der Veen Ruben Seggers Peter Bloem and Giorgio Patrini. 2018. Three Tools for Practical Differential Privacy. arXiv:1812.02890 [stat.ML]"},{"key":"e_1_3_2_1_27_1","volume-title":"Differentially private empirical risk minimization revisited: Faster and more general. Advances in Neural Information Processing Systems 30","author":"Wang Di","year":"2017","unstructured":"Di Wang, Minwei Ye, and Jinhui Xu. 2017. Differentially private empirical risk minimization revisited: Faster and more general. Advances in Neural Information Processing Systems 30 (2017)."},{"key":"e_1_3_2_1_28_1","volume-title":"Balancing differential privacy and utility: A relevance-based adaptive private fine-tuning framework for language models","author":"Wang Naiyu","year":"2024","unstructured":"Naiyu Wang, Shen Wang, Meng Li, Longfei Wu, Zijian Zhang, Zhitao Guan, and Liehuang Zhu. 2024. Balancing differential privacy and utility: A relevance-based adaptive private fine-tuning framework for language models. IEEE Transactions on Information Forensics and Security (2024)."},{"key":"e_1_3_2_1_29_1","volume-title":"DC-SGD: Differentially Private SGD with Dynamic Clipping through Gradient Norm Distribution Estimation","author":"Wei Chengkun","year":"2025","unstructured":"Chengkun Wei, Weixian Li, Gong Chen, and Wenzhi Chen. 2025. DC-SGD: Differentially Private SGD with Dynamic Clipping through Gradient Norm Distribution Estimation. IEEE Transactions on Information Forensics and Security (2025)."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM41043.2020.9155359"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/BigData50022.2020.9378171"},{"key":"e_1_3_2_1_32_1","first-page":"21270","article-title":"Characterization of excess risk for locally strongly convex population risk","volume":"35","author":"Yi Mingyang","year":"2022","unstructured":"Mingyang Yi, Ruoyu Wang, and Zhi-Ming Ma. 2022. Characterization of excess risk for locally strongly convex population risk. Advances in Neural Information Processing Systems 35 (2022), 21270\u201321285.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_33_1","volume-title":"Opacus: User-friendly differential privacy library in PyTorch. arXiv preprint arXiv.2109.12298","author":"Yousefpour Ashkan","year":"2021","unstructured":"Ashkan Yousefpour, Igor Shilov, Alexandre Sablayrolles, Davide Testuggine, Karthik Prasad, Mani Malek, John Nguyen, Sayan Ghosh, Akash Bharadwaj, Jessica Zhao, et al. 2021. Opacus: User-friendly differential privacy library in PyTorch. arXiv preprint arXiv.2109.12298 (2021)."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2019.00019"},{"key":"e_1_3_2_1_35_1","volume-title":"Efficient private ERM for smooth objectives. arXiv preprint arXiv: 1703.09947","author":"Zhang Jiaqi","year":"2017","unstructured":"Jiaqi Zhang, Kai Zheng, Wenlong Mou, and Liwei Wang. 2017. Efficient private ERM for smooth objectives. arXiv preprint arXiv: 1703.09947 (2017)."}],"event":{"name":"ASIA CCS '26: ACM Asia Conference on Computer and Communications Security","location":"Bangalore India","acronym":"ASIA CCS '26","sponsor":["SIGSAC ACM Special Interest Group on Security, Audit, and Control"]},"container-title":["Proceedings of the ACM Asia Conference on Computer and Communications Security"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3779208.3805970","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T15:41:51Z","timestamp":1780587711000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3779208.3805970"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":35,"alternative-id":["10.1145\/3779208.3805970","10.1145\/3779208"],"URL":"https:\/\/doi.org\/10.1145\/3779208.3805970","relation":{},"subject":[],"published":{"date-parts":[[2026,6]]},"assertion":[{"value":"2026-06-04","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}