AAAI 2023 accepted papers on Federated learning and privacy

Privacy attacks and secure learning · 15 papers

• Securing Secure Aggregation: Mitigating Multi-Round Privacy Leakage in Federated Learning (63 citations)
• On the Vulnerability of Backdoor Defenses for Federated Learning (55 citations)
• Industry-Scale Orchestrated Federated Learning for Drug Discovery (51 citations)
• Win-Win: A Privacy-Preserving Federated Framework for Dual-Target Cross-Domain Recommendation (44 citations)
• DeFL: Defending against Model Poisoning Attacks in Federated Learning via Critical Learning Periods Awareness (43 citations)
• PateGail: A Privacy-Preserving Mobility Trajectory Generator with Imitation Learning (25 citations)
• PPGenCDR: A Stable and Robust Framework for Privacy-Preserving Cross-Domain Recommendation (25 citations)
• Dropout Is NOT All You Need to Prevent Gradient Leakage (18 citations)
• Incentive-Boosted Federated Crowdsourcing (17 citations)
• XRand: Differentially Private Defense against Explanation-Guided Attacks (12 citations)
• People Taking Photos That Faces Never Share: Privacy Protection and Fairness Enhancement from Camera to User (8 citations)
• Conflicting Interactions among Protection Mechanisms for Machine Learning Models (7 citations)

and 3 more in the interactive map.

Personalized and heterogeneous FL · 11 papers

• FedALA: Adaptive Local Aggregation for Personalized Federated Learning (414 citations)
• FairFed: Enabling Group Fairness in Federated Learning (177 citations)
• Tackling Data Heterogeneity in Federated Learning with Class Prototypes (121 citations)
• Efficient Distribution Similarity Identification in Clustered Federated Learning via Principal Angles between Client Data Subspaces (92 citations)
• Federated Generative Model on Multi-Source Heterogeneous Data in IoT (51 citations)
• Federated Robustness Propagation: Sharing Adversarial Robustness in Heterogeneous Federated Learning (24 citations)
• FedGS: Federated Graph-Based Sampling with Arbitrary Client Availability (19 citations)
• FedNP: Towards Non-IID Federated Learning via Federated Neural Propagation (18 citations)
• FedABC: Targeting Fair Competition in Personalized Federated Learning (10 citations)
• Bayesian Federated Neural Matching That Completes Full Information (2 citations)
• A Federated Learning Monitoring Tool for Self-Driving Car Simulation (Student Abstract)

Differential privacy · 9 papers

• Differentially Private Learning with Per-Sample Adaptive Clipping (22 citations)
• Echo of Neighbors: Privacy Amplification for Personalized Private Federated Learning with Shuffle Model (13 citations)
• Integer Subspace Differential Privacy (7 citations)
• Differentially Private Fair Division (6 citations)
• Differentially Private Heatmaps (6 citations)
• Differentially Private Nonlinear Causal Discovery from Numerical Data (5 citations)
• DPAUC: Differentially Private AUC Computation in Federated Learning (5 citations)
• Differentially Private Condorcet Voting (3 citations)
• Two Views of Constrained Differential Privacy: Belief Revision and Update

Communication-efficient FL · 8 papers

• Faster Adaptive Federated Learning (86 citations)
• Layer-Wise Adaptive Model Aggregation for Scalable Federated Learning (64 citations)
• Complement Sparsification: Low-Overhead Model Pruning for Federated Learning (46 citations)
• Beyond ADMM: A Unified Client-Variance-Reduced Adaptive Federated Learning Framework (30 citations)
• Efficient Training of Large-Scale Industrial Fault Diagnostic Models through Federated Opportunistic Block Dropout (8 citations)
• Almost Cost-Free Communication in Federated Best Arm Identification (6 citations)
• Clustered Federated Learning for Heterogeneous Data (Student Abstract) (6 citations)
• CDMA: A Practical Cross-Device Federated Learning Algorithm for General Minimax Problems (2 citations)