backdoor attack

Efficient but Vulnerable: Benchmarking and Defending LLM Batch Prompting Attack ACL 2025 ELBA-Bench: An Efficient Learning Backdoor Attacks Benchmark for Large Language Models ACL 2025 Energy-based Backdoor Defense Against Federated Graph Learning ICLR 2025 Exploring Backdoor Vulnerabilities of Chat Models COLING 2025 FedDLAD: A Federated Learning Dual-Layer Anomaly Detection Framework for Enhancing Resilience Against Backdoor Attacks IJCAI 2025 Fine-grained Prompt Screening: Defending Against Backdoor Attack on Text-to-Image Diffusion Models IJCAI 2025 Forget the Unneeded: Backdooring Large Language Models via Contrastive-enhanced Machine Unlearning EMNLP 2025 Fusing Pruned and Backdoored Models: Optimal Transport-based Data-free Backdoor Mitigation AAAI 2025 Gracefully Filtering Backdoor Samples for Generative Large Language Models without Retraining COLING 2025 GraphProt: Certified Black-Box Shielding Against Backdoored Graph Models IJCAI 2025 Hidden Ghost Hand: Unveiling Backdoor Vulnerabilities in MLLM-Powered Mobile GUI Agents EMNLP 2025 HoneypotNet: Backdoor Attacks Against Model Extraction AAAI 2025 IBAS:Imperceptible Backdoor Attacks in Split Learning with Limited Information AAAI 2025 ICLShield: Exploring and Mitigating In-Context Learning Backdoor Attacks ICML 2025 Identify Backdoored Model in Federated Learning via Individual Unlearning WACV 2025 Infighting in the Dark: Multi-Label Backdoor Attack in Federated Learning CVPR 2025 Influence-Based Fair Selection for Sample-Discriminative Backdoor Attack AAAI 2025 Injecting Universal Jailbreak Backdoors into LLMs in Minutes ICLR 2025 Invisible Backdoor Attack against Self-supervised Learning CVPR 2025 Is Poisoning a Real Threat to DPO? Maybe More So Than You Think AAAI 2025 Jailbreak-Tuning: Models Efficiently Learn Jailbreak Susceptibility EMNLP 2025 Label-Free Backdoor Attacks in Vertical Federated Learning AAAI 2025 Localizing Malicious Outputs from CodeLLM EMNLP 2025 LoRATK: LoRA Once, Backdoor Everywhere in the Share-and-Play Ecosystem EMNLP 2025 Low-Frequency Black-Box Backdoor Attack via Evolutionary Algorithm WACV 2025