Decentralized Adversarial Training over Graphs
Not on the map. Why?
Abstract (arXiv)
The vulnerability of machine learning models to adversarial attacks has been attracting considerable attention in recent years. Most existing studies focus on the behavior of stand-alone single-agent learners. In comparison, this work studies adversarial training over graphs, where individual agents are subjected to perturbations of varied strength levels across space. It is expected that interactions by linked agents, and the heterogeneity of the attack models that are possible over the graph, can help enhance robustness in view of the coordination power of the group. Using a min-max formulation of distributed learning, we develop a decentralized adversarial training framework for multi-agent systems. Specifically, we devise two decentralized adversarial training algorithms by relying on two popular decentralized learning strategies--diffusion and consensus. We analyze the convergence properties of the proposed framework for strongly-convex, convex, and non-convex environments, and illustrate the enhanced robustness to adversarial attacks.
Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 51 of its 80 references that are in the map. First posted on arXiv 23 Mar 2023.
Builds on
51 of 80 references.
References · 51
- 2014Explaining and Harnessing Adversarial Examplescited by 7,287
- 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
- 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
- 2013Intriguing properties of neural networkscited by 5,114
- 2019Theoretically Principled Trade-off between Robustness and Accuracycited by 1,510
- 2016On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minimacited by 1,337
- 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,315
- 2017Visualizing the Loss Landscape of Neural Netscited by 1,126
- 2020Fast is better than free: Revisiting adversarial trainingcited by 723
- 2015Distillation as a Defense to Adversarial Perturbations against Deep Neural Networkscited by 675
- 2017Adversarial Examples for Evaluating Reading Comprehension Systemscited by 568
- 2017Decision-Based Adversarial Attacks: Reliable Attacks Against Black-Box Machine Learning Modelscited by 459
38 more
- 2017Robust Adversarial Reinforcement Learningcited by 439
- 2017Certifying Some Distributional Robustness with Principled Adversarial Trainingcited by 333
- 2016Adversarial Training Methods for Semi-Supervised Text Classificationcited by 280
- 2021Recent Advances in Adversarial Training for Adversarial Robustnesscited by 276
- 2019On Gradient Descent Ascent for Nonconvex-Concave Minimax Problemscited by 266
- 2017PixelDefend: Leveraging Generative Models to Understand and Defend against Adversarial Examplescited by 243
- 2018Adversarial Logit Pairingcited by 224
- 2019Topology Attack and Defense for Graph Neural Networks: An Optimization Perspectivecited by 196
- 2019Adversarial Training and Robustness for Multiple Perturbationscited by 182
- 2013On the Convergence of Decentralized Gradient Descentcited by 158
- 2023Handbook of Convergence Theorems for (Stochastic) Gradient Methodscited by 158
- 2018Stochastic model-based minimization of weakly convex functionscited by 157
- 2014Towards Deep Neural Network Architectures Robust to Adversarial Examplescited by 146
- 2019Adversarial Robustness through Local Linearizationcited by 146
- 2021PixMix: Dreamlike Pictures Comprehensively Improve Safety Measurescited by 131
- 2021On the Convergence and Robustness of Adversarial Trainingcited by 127
- 2022Robustness and Accuracy Could Be Reconcilable by (Proper) Definitioncited by 109
- 2019Graph Adversarial Training: Dynamically Regularizing Based on Graph Structurecited by 93
- 2019Adversarial Robustness Against the Union of Multiple Perturbation Modelscited by 88
- 2019Efficient Algorithms for Smooth Minimax Optimizationcited by 75
- 2021Fast Minimum-norm Adversarial Attacks through Adaptive Norm Constraintscited by 50
- 2022Topology-aware Generalization of Decentralized SGDcited by 37
- 2015Foveation-based Mechanisms Alleviate Adversarial Examplescited by 32
- 2020Dif-MAML: Decentralized Multi-Agent Meta-Learningcited by 26
- 2022Byzantine-Resilient Decentralized Stochastic Optimization with Robust Aggregation Rulescited by 23
- 2019Distributed Learning in Non-Convex Environments -- Part I: Agreement at a Linear Ratecited by 22
- 2013On the Learning Behavior of Adaptive Networks - Part I: Transient Analysiscited by 20
- 2021Adversarial attacks in consensus-based multi-agent reinforcement learningcited by 17
- 2022Federated Adversarial Learning: A Framework with Convergence Analysiscited by 17
- 2019GraphDefense: Towards Robust Graph Convolutional Networkscited by 16
- 2019Distributed Learning in Non-Convex Environments -- Part II: Polynomial Escape from Saddle-Pointscited by 13
- 2021Concurrent Adversarial Learning for Large-Batch Trainingcited by 11
- 2019Decentralized Heterogeneous Multi-Player Multi-Armed Bandits with Non-Zero Rewards on Collisionscited by 10
- 2022Distributed Adversarial Training to Robustify Deep Neural Networks at Scalecited by 9
- 2019Revisiting Randomized Gossip Algorithms: General Framework, Convergence Rates and Novel Block and Accelerated Protocolscited by 5
- 2017Performance Limits of Stochastic Sub-Gradient Learning, Part II: Multi-Agent Casecited by 3
- 2023Multi-Agent Adversarial Training Using Diffusion Learningcited by 2
- 2021Quickest Inference of Network Cascades with Noisy Informationcited by 1
50 most cited of 51 All 51 (JSON)
Built on by
Citing papers per year: 2023: 1; 2024: 0; 2025: 2.
3 papers.