model poisoning

Breaking Cross-View Associations: Byzantine Model Poisoning Attack against Vertical Federated Learning AAAI 2026 Eliminate Distance Differences Induced by Backdoor Attacks: Layer-Selective Training and Clipping to Mask Backdoor Models CVPR 2026 Good Gradients Poison Your Model: Evading Defenses in Federated Learning via Boundary-adaptive Perturbation AAAI 2026 Persistent Backdoor Attacks Under Continual Fine-Tuning of LLMs AAAI 2026 Poisoning with a Pill: Circumventing Detection in Federated Learning AAAI 2026 Backdoor-Powered Prompt Injection Attacks Nullify Defense Methods EMNLP 2025 Defending Against Sophisticated Poisoning Attacks with RL-based Aggregation in Federated Learning AAAI 2025 FedHAN: A Cache-Based Semi-Asynchronous Federated Learning Framework Defending Against Poisoning Attacks in Heterogeneous Clients IJCAI 2025 IBAS:Imperceptible Backdoor Attacks in Split Learning with Limited Information AAAI 2025 Mind the Cost of Scaffold! Benign Clients May Even Become Accomplices of Backdoor Attack ICCV 2025 Model Poisoning Attacks to Federated Learning via Multi-Round Consistency CVPR 2025 Performance Guaranteed Poisoning Attacks in Federated Learning: A Sliding Mode Approach IJCAI 2025 Poisoning Bayesian Inference via Data Deletion and Replication AISTATS 2025 SADBA: Self-Adaptive Distributed Backdoor Attack Against Federated Learning AAAI 2025 Adversarial Attacks on Federated-Learned Adaptive Bitrate Algorithms AAAI 2024 Backdoor Federated Learning by Poisoning Backdoor-Critical Layers ICLR 2024 Backdoor NLP Models via AI-Generated Text COLING 2024 Beyond Traditional Threats: A Persistent Backdoor Attack on Federated Learning AAAI 2024 Chronic Poisoning: Backdoor Attack against Split Learning AAAI 2024 DarkFed: A Data-Free Backdoor Attack in Federated Learning IJCAI 2024 Data Free Backdoor Attacks NeurIPS 2024 EAB-FL: Exacerbating Algorithmic Bias through Model Poisoning Attacks in Federated Learning IJCAI 2024 HYDRA-FL: Hybrid Knowledge Distillation for Robust and Accurate Federated Learning NeurIPS 2024 Privacy Backdoors: Enhancing Membership Inference through Poisoning Pre-trained Models NeurIPS 2024 Re-thinking Data Availability Attacks Against Deep Neural Networks CVPR 2024