backdoor attack

6DAttack: Backdoor Attacks in the 6DoF Pose Estimation AAAI 2026 Activation Decomposition and Steering for LLM Backdoor Remediation ACL 2026 AdapAction: Adaptive Target Action Backdoor Attack against GUI Agents CVPR 2026 AdvBDGen: A Robust Framework for Generating Adaptive and Stealthy Backdoors in LLM Alignment AAAI 2026 AutoDebias: An Automated Framework for Detecting and Mitigating Backdoor Biases in Text-to-Image Models CVPR 2026 Backdoor Attacks on Open Vocabulary Object Detectors via Multi-Modal Prompt Tuning AAAI 2026 Backdoor Collapse: Eliminating Unknown Threats Via Known Backdoor Aggregation In Language Models ACL 2026 Backdooring Rationalization AAAI 2026 Backdoors in RLVR: Jailbreak Backdoors in LLMs From Verifiable Reward ACL 2026 BadThink: Triggered Overthinking Attacks on Chain-of-Thought Reasoning in Large Language Models AAAI 2026 Batman: Benign Knowledge Alignment Through Malicious Null Space in Federated Backdoor Attack CVPR 2026 Beyond Immediate Activation: Temporally Decoupled Backdoor Attacks on Time Series Forecasting AAAI 2026 Beyond Training-time Poisoning: Component-level and Post-training Backdoors in Deep Reinforcement Learning AAAI 2026 BlackMirror: Black-Box Backdoor Detection for Text-to-Image Models via Instruction-Response Deviation CVPR 2026 Breaking the Stealth-Potency Trade-off in Clean-Image Backdoors with Generative Trigger Optimization AAAI 2026 Clean-Label Physical Backdoor Attacks with Data Distillation AAAI 2026 Compiling Activation Steering into Weights via Null-Space Constraints for Stealthy Backdoors ACL 2026 Critical-CoT: A Robust Defense Framework against Reasoning-Level Backdoor Attacks in Large Language Models ACL 2026 DoBlock: Blocking Malicious Association Propagation for Backdoor-Robust Federated Learning Under Domain Skew AAAI 2026 Dormant Backdoor: Weaponizing Model Finetuning for Feasible Backdoor Attacks Against Pretrained Models AAAI 2026 Eliminate Distance Differences Induced by Backdoor Attacks: Layer-Selective Training and Clipping to Mask Backdoor Models CVPR 2026 Enhancing All-to-X Backdoor Attacks with Optimized Target Class Mapping AAAI 2026 Exposing Functional Fusion: A New Class of Strategic Backdoor in Dynamic Prompt Architectures CVPR 2026 FILTER: A Framework for Defending Against Backdoor Attacks in Vertical Federated Learning AAAI 2026 FlowHijack: A Dynamics-Aware Backdoor Attack on Flow-Matching Vision-Language-Action Models CVPR 2026