Distributed Learning with Adversarial Gradient Perturbations
Privacy concerns in distributed learning often lead clients to return intentionally altered gradient information. We consider the problem of learning convex and $L$-smooth functions under adversarial gradient perturbation, where a client's gradient reply to a server query can deviate arbitrarily from the true gradient subject to a distance bound. Our study focuses on two fundamental questions: (i) what is the smallest achievable sub-optimality gap (i.e., excess error in optimization) under such responses, and (ii) how many queries are sufficient to guarantee a given sub-optimality gap? We establish tight feasibility thresholds on the sub-optimality gap and provide algorithms that achieve these thresholds with provable query complexity guarantees.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Certifiably-Robust Federated Adversarial Learning via Randomized Smoothing
Federated learning is an emerging data-private distributed learning framework, which, however, is vulnerable to adversarial attacks. Although several heuristic defenses are proposed to enhance the robustness of federated…
Federated LearningRobust Combination of Distributed Gradients Under Adversarial Perturbations
We consider distributed (gradient descent-based) learning scenarios where the server combines the gradients of learning objectives gathered from local clients. As individual data collection and learning environments …
Adversarial Effects on Expressibility and Trainability in Distributed Variational Quantum Algorithms
Distributed quantum algorithms offer a promising pathway to scale variational quantum algorithms beyond the constraints of noisy intermediate-scale quantum hardware. However, existing approaches implicitly assume a trust…
Distributed Adversarial Training to Robustify Deep Neural Networks at Scale
Current deep neural networks (DNNs) are vulnerable to adversarial attacks, where adversarial perturbations to the inputs can change or manipulate classification. To defend against such attacks, an effective and popular a…
Distributed OptimizationAnalyzing Inference Privacy Risks Through Gradients in Machine Learning
In distributed learning settings, models are iteratively updated with shared gradients computed from potentially sensitive user data. While previous work has studied various privacy risks of sharing gradients, our paper …
Attribute