Backdoor and data poisoning attacks can achieve high attack success while evading existing spectral and optimisation based defences. We show that this behaviour is not incidental, but arises from a fundamental geometric mechanism in input space. Using kernel ridge regression as an exact model of wide neural networks, we prove that clustered dirty label poisons induce a rank one spike in the input Hessian whose magnitude scales quadratically with attack efficacy. Crucially, for nonlinear kernels we identify a near clone regime in which poison efficacy remains order one while the induced input curvature vanishes, making the attack provably spectrally undetectable. We further show that input gradient regularisation contracts poison aligned Fisher and Hessian eigenmodes under gradient flow, yielding an explicit and unavoidable safety efficacy trade off by reducing data fitting capacity. For exponential kernels, this defence admits a precise interpretation as an anisotropic high pass filter that increases the effective length scale and suppresses near clone poisons. Extensive experiments on linear models and deep convolutional networks across MNIST and CIFAR 10 and CIFAR 100 validate the theory, demonstrating consistent lags between attack success and spectral visibility, and showing that regularisation and data augmentation jointly suppress poisoning. Our results establish when backdoors are inherently invisible, and provide the first end to end characterisation of poisoning, detectability, and defence through input space curvature.
Sparsification Under Siege: Dual-Level Defense Against Poisoning in Communication-Efficient Federated Learning
School of Computer Science and Engineering, Beihang University（北京航空航天大学计算机科学与工程学院）；School of Cyber Science and Technology at Beihang University（北京航空航天大学网络安全科学与技术学院）；School of Cyberspace Science and Technology, Beijing Jiaotong University（北京交通大学网络空间科学与技术学院）；Beijing Key Laboratory of Security and Privacy in Intelligent Transportation（北京智能交通安全与隐私重点实验室）；Zhongguancun Laboratory（中关村实验室）；School of Computing and Information,University of Pittsburgh（匹兹堡大学计算与信息学院）
Robust Estimation of Sparse Numerical Vectors under Local Differential Privacy
Shenzhen Campus of Sun Yat-sen University（中山大学深圳校区）；Zhejiang University（浙江大学）；Guangzhou University（广州大学）；National Interdisciplinary Research Center of Engineering Physics（国家工程物理学跨学科研究中心）；Anhui University of Science and Technology（安徽理工大学）
Towards Effective Evaluations and Comparisons for LLM Unlearning Methods
Hong Kong Baptist University（香港浸会大学）；RIKEN Center for Advanced Intelligence Project（理化学研究所先进智能项目中心）；The University of Sydney（悉尼大学）；The University of Tokyo（东京大学）
Privacy, Robustness, and Fairness Trade-offs in Federated Intrusion Detection: Geometric Indistinguishability at the Aggregation Interface
Bangladesh University of Business and Technology (BUBT)（孟加拉国商业与技术大学（BUBT））；Jagannath University（贾格纳特大学）；University of New South Wales (UNSW)（新南威尔士大学（UNSW））
Secure Distributed/Federated Learning: Prediction-Privacy Trade-Off for Multi-Agent System
University of Southern California（南加州大学）
分散学习是一种有效的新兴范式，用于提高多个有界计算代理的计算能力。在大数据时代，在分布式和联邦学习（DL和FL）框架内执行推理，中央服务器需要处理大量数据，同时依赖各种代理执行多个分布式训练任务。考虑到分布式计算的拓扑结构，隐私已经成为一个首要的问题。此外，假设代理的信息处理能力有限，需要一个复杂的\textit{privacy-preserving decentralization}来确保有效的计算。为此，我们研究的\textit{privacy-aware server to multi-agent assignment}问题受到信息处理的限制与每个代理，同时保持隐私和确保学习信息的消息，通过分布式私人联邦学习（DPFL）的方法收到代理全球终端。为了找到一个分散的计划，两个代理系统，我们制定了一个优化问题，平衡隐私和准确性，考虑到与每个代理相关联的压缩约束的质量。我们提出了一个迭代收敛算法交替自洽方程。我们还对所提出的解决方案进行了数值评估，以显示隐私预测的权衡，并证明了新方法在确保DL和FL隐私方面的有效性。
