Skip to content
conftrace_

poisoning attack

121 papers

Explore in graph

Co-occurring keywords · papers mentioning both

backdoor attack (38) adversarial attack (28) adversarial learning (25) federated learning (17) data poisoning (16) adversarial robustness (14) adversarial defense (11) graph neural network (11) evasion attack (8) model poisoning (8)

Papers

Performance Guaranteed Poisoning Attacks in Federated Learning: A Sliding Mode Approach IJCAI 2025 Poisoning-based Backdoor Attacks for Arbitrary Target Label with Positive Triggers IJCAI 2025 Poison-splat: Computation Cost Attack on 3D Gaussian Splatting ICLR 2025 Protecting Model Adaptation from Trojans in the Unlabeled Data AAAI 2025 Single-agent Poisoning Attacks Suffice to Ruin Multi-Agent Learning ICLR 2025 StealthAttack: Robust 3D Gaussian Splatting Poisoning via Density-Guided Illusions ICCV 2025 Targeted Attack Improves Protection against Unauthorized Diffusion Customization ICLR 2025 TrendSim: Simulating Trending Topics in Social Media Under Poisoning Attacks with LLM-based Multi-agent System NAACL 2025 When and Where do Data Poisons Attack Textual Inversion? ICCV 2025 AgentPoison: Red-teaming LLM Agents via Poisoning Memory or Knowledge Bases NeurIPS 2024 Attack To Defend: Exploiting Adversarial Attacks for Detecting Poisoned Models CVPR 2024 BadRL: Sparse Targeted Backdoor Attack against Reinforcement Learning AAAI 2024 Boosting the Adversarial Robustness of Graph Neural Networks: An OOD Perspective ICLR 2024 ContextCite: Attributing Model Generation to Context NeurIPS 2024 DataElixir: Purifying Poisoned Dataset to Mitigate Backdoor Attacks via Diffusion Models AAAI 2024 Deceptive Fairness Attacks on Graphs via Meta Learning ICLR 2024 Demystifying Poisoning Backdoor Attacks from a Statistical Perspective ICLR 2024 Dual Defense: Enhancing Privacy and Mitigating Poisoning Attacks in Federated Learning NeurIPS 2024 Improving Robustness of GNN-based Anomaly Detection by Graph Adversarial Training COLING 2024 Like Oil and Water: Group Robustness Methods and Poisoning Defenses May Be at Odds ICLR 2024 lpNTK: Better Generalisation with Less Data via Sample Interaction During Learning ICLR 2024 Position: Exploring the Robustness of Pipeline-Parallelism-Based Decentralized Training ICML 2024 Privacy Backdoors: Enhancing Membership Inference through Poisoning Pre-trained Models NeurIPS 2024 Private Truly-Everlasting Robust-Prediction ICML 2024 Provable Robustness against a Union of L_0 Adversarial Attacks AAAI 2024