2023年1月20日
【五期邹昱夫】USENIX Security（USENIX Security'18）AttriGuard: A Practical Defense Against Attribute Inference Attacks via Adversarial Machine Learning
摘要： "Jia, Jinyuan, and Neil Zhenqiang Gong. "AttriGuard: A practical defense against attribute inference attacks via adversarial machine learning." 27th U 阅读全文
posted @ 2023-01-20 16:25 方班隐私保护小组 阅读(92) 评论(0) 推荐(0)
2023年1月13日
【五期邹昱夫】Enhanced Membership Inference Attacks against Machine Learning Models
摘要： "arXiv:2111.09679, 2021." 文章关注机器学习模型的隐私泄露问题，成员推理攻击：给出一条样本，可以推断该样本是否在模型的训练数据集中——即便对模型的参数、结构知之甚少，该攻击仍然有效。本质还是使用影子模型的方法训练攻击模型。但是针对攻击者不知道目标模型的训练集，文章提出了影子学 阅读全文
posted @ 2023-01-13 19:00 方班隐私保护小组 阅读(166) 评论(0) 推荐(0)
【五期伍捷威】CCF-A(ICDE’19) SecEQP: A Secure and Efficient Scheme for SkNN Query Problem over Encrypted Geodata on Cloud
摘要： X. Lei, A. X. Liu, R. Li and G. -H. Tu, "SecEQP: A Secure and Efficient Scheme for SkNN Query Problem Over Encrypted Geodata on Cloud," 2019 IEEE 35th 阅读全文
posted @ 2023-01-13 18:55 方班隐私保护小组 阅读(45) 评论(0) 推荐(0)
【五期邵润东】CCF-A(TMC'21)Distillation-Based Semi-Supervised Federated Learning for Communication-Efficient Collaborative Training with Non-IID Private Data
摘要： Itahara, Sohei, et al. "Distillation-based semi-supervised federated learning for communication-efficient collaborative training with non-iid private 阅读全文
posted @ 2023-01-13 18:09 方班隐私保护小组 阅读(200) 评论(0) 推荐(0)
【五期邹昱夫】CCF-A（IEEE T-PAMI'22）Fedipr: Ownership verification for federated deep neural network models
摘要： Li, Bowen, et al. "Fedipr: Ownership verification for federated deep neural network models." IEEE Transactions on Pattern Analysis and Machine Intelli 阅读全文
posted @ 2023-01-13 17:12 方班隐私保护小组 阅读(226) 评论(0) 推荐(0)
【五期梁锐】CCF-A(USENIX'22)ML-Doctor: Holistic Risk Assessment of Inference Attacks Against Machine Learning Models
摘要： Liu, Yugeng, et al. "ML-Doctor: Holistic risk assessment of inference attacks against machine learning models." arXiv preprint arXiv:2102.02551 (2021) 阅读全文
posted @ 2023-01-13 16:39 方班隐私保护小组 阅读(80) 评论(0) 推荐(0)
【五期邵润东】CCF-B(INS'21)A privacy-preserving and non-interactive federated learning scheme for regression training with gradient descent
摘要： Wang, Fengwei, et al. "A privacy-preserving and non-interactive federated learning scheme for regression training with gradient descent." Information 阅读全文
posted @ 2023-01-13 16:02 方班隐私保护小组 阅读(79) 评论(0) 推荐(0)
【五期杨志】CCF-A（CVPR'22）Balanced Multimodal Learning via On-the-fly Gradient Modulation
摘要： Peng, Xiaokang, et al. "Balanced Multimodal Learning via On-the-fly Gradient Modulation." Proceedings of the IEEE/CVF Conference on Computer Vision an 阅读全文
posted @ 2023-01-13 15:51 方班隐私保护小组 阅读(165) 评论(0) 推荐(0)
【五期李伟平】CCF-A（NeurIPS'19）privacy preserving classification of personal text messages with secure multi party computation Paper
摘要： Devin Reich, Ariel Todoki, Rafael Dowsley, Martine De Cock, Anderson Nascimento. 2019. Privacy-Preserving Classification of Personal Text Messages wit 阅读全文
posted @ 2023-01-13 14:26 方班隐私保护小组 阅读(47) 评论(0) 推荐(0)
【五期李伟平】CCF-A（USENIX Security'20）Secure Multi-party Computation of Differentially Private Median
摘要： Jonas Böhler and Florian Kerschbaum. 2020. Secure Multi-party Computation of Differentially Private Median. In the Proceedings of the 29th USENIX Secu 阅读全文
posted @ 2023-01-13 14:14 方班隐私保护小组 阅读(104) 评论(0) 推荐(0)