随笔分类 - 【五期邹昱夫】
摘要：> "Zhang, Zhuosheng, et al. "SAFELearning: Secure Aggregation in Federated Learning with Backdoor Detectability." IEEE Transactions on Information For
阅读全文
摘要：> "Li, Haoyang, et al. "3DFed: Adaptive and Extensible Framework for Covert Backdoor Attack in Federated Learning." 2023 IEEE Symposium on Security an
阅读全文
摘要：> "Gu, Tianyu, et al. "Badnets: Evaluating backdooring attacks on deep neural networks." IEEE Access 7 (2019): 47230-47244." 本文提出了外包机器学习时选择值得信赖的提供商的重要
阅读全文
摘要：> "Liu, Kang, Brendan Dolan-Gavitt, and Siddharth Garg. "Fine-pruning: Defending against backdooring attacks on deep neural networks." Research in Att
阅读全文
摘要：> "Wang, Haotao, et al. "Trap and Replace: Defending Backdoor Attacks by Trapping Them into an Easy-to-Replace Subnetwork." Advances in Neural Informa
阅读全文
摘要：> "Wu, Dongxian, and Yisen Wang. "Adversarial neuron pruning purifies backdoored deep models." Advances in Neural Information Processing Systems 34 (2
阅读全文
摘要："Jia X, Zhang Y, Wu B, et al. LAS-AT: adversarial training with learnable attack strategy[C]//Proceedings of the IEEE/CVF Conference on Computer Visio
阅读全文
摘要："Jeon J, Lee K, Oh S, et al. Gradient inversion with generative image prior[J]. Advances in neural information processing systems, 2021, 34: 29898-299
阅读全文
摘要："Geiping J, Bauermeister H, Dröge H, et al. Inverting gradients-how easy is it to break privacy in federated learning?[J]. Advances in Neural Informat
阅读全文
摘要："Zhao B, Mopuri K R, Bilen H. idlg: Improved deep leakage from gradients[J]. arXiv preprint arXiv:2001.02610, 2020." 本文发现共享梯度肯定会泄露数据真实标签。我们提出了一种简单但可靠的
阅读全文
摘要："Zhu, Ligeng, Zhijian Liu, and Song Han. "Deep leakage from gradients." Advances in neural information processing systems 32 (2019)." 本文从公开共享的梯度中获得私有训
阅读全文
摘要："Liu, Yiyong, et al. "Membership inference attacks by exploiting loss trajectory." Proceedings of the 2022 ACM SIGSAC Conference on Computer and Commu
阅读全文
摘要："Rezaei, Shahbaz, and Xin Liu. "On the difficulty of membership inference attacks." Proceedings of the IEEE/CVF Conference on Computer Vision and Patt
阅读全文
摘要："Nasr M, Songi S, Thakurta A, et al. Adversary instantiation: Lower bounds for differentially private machine learning[C]//2021 IEEE Symposium on secu
阅读全文
摘要："Jayaraman B, Evans D. Evaluating differentially private machine learning in practice[C]//USENIX Security Symposium. 2019." 本文对机器学习不同隐私机制进行评估。评估重点放在梯度
阅读全文
摘要："Salem A, Wen R, Backes M, et al. Dynamic backdoor attacks against machine learning models[C]//2022 IEEE 7th European Symposium on Security and Privac
阅读全文
摘要："Song C, Shmatikov V. Auditing data provenance in text-generation models[C]//Proceedings of the 25th ACM SIGKDD International Conference on Knowledge
阅读全文
摘要："Carlini, Nicholas, et al. "Membership inference attacks from first principles." 2022 IEEE Symposium on Security and Privacy (SP). IEEE, 2022." 本文认为成员
阅读全文
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
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
