model security

BeDKD: Backdoor Defense Based on Directional Mapping Module and Adversarial Knowledge Distillation AAAI 2026 Beyond Training-time Poisoning: Component-level and Post-training Backdoors in Deep Reinforcement Learning AAAI 2026 EigenShield: Inference-Time, Model-Agnostic Jailbreaking Defense via Causal Subspace Filtering AAAI 2026 Framework GNN-AID: Graph Neural Network Analysis, Interpretation and Defense AAAI 2026 Towards Effective, Stealthy, and Persistent Backdoor Attacks Targeting Graph Foundation Models AAAI 2026 Backdoor Attacks on Neural Networks via One-Bit Flip ICCV 2025 BadToken: Token-level Backdoor Attacks to Multi-modal Large Language Models CVPR 2025 Beyond the Tip of Efficiency: Uncovering the Submerged Threats of Jailbreak Attacks in Small Language Models ACL 2025 Bit-Flip Induced Latency Attacks in Object Detection WACV 2025 DF-MIA: A Distribution-Free Membership Inference Attack on Fine-Tuned Large Language Models AAAI 2025 DISTIL: Data-Free Inversion of Suspicious Trojan Inputs via Latent Diffusion ICCV 2025 Efficient Robustness Evaluation via Constraint Relaxation AAAI 2025 ELBA-Bench: An Efficient Learning Backdoor Attacks Benchmark for Large Language Models ACL 2025 Exploring Backdoor Vulnerabilities of Chat Models COLING 2025 from Benign import Toxic: Jailbreaking the Language Model via Adversarial Metaphors ACL 2025 From Trade-off to Synergy: A Versatile Symbiotic Watermarking Framework for Large Language Models ACL 2025 Gracefully Filtering Backdoor Samples for Generative Large Language Models without Retraining COLING 2025 Guardrails and Security for LLMs: Safe, Secure and Controllable Steering of LLM Applications ACL 2025 Infighting in the Dark: Multi-Label Backdoor Attack in Federated Learning CVPR 2025 Intrinsic Model Weaknesses: How Priming Attacks Unveil Vulnerabilities in Large Language Models NAACL 2025 Is Poisoning a Real Threat to DPO? Maybe More So Than You Think AAAI 2025 LLMs are Privacy Erasable EMNLP 2025 Medical MLLM Is Vulnerable: Cross-Modality Jailbreak and Mismatched Attacks on Medical Multimodal Large Language Models AAAI 2025 Obliviate: Neutralizing Task-agnostic Backdoors within the Parameter-efficient Fine-tuning Paradigm NAACL 2025 On the Adversarial Risk of Test Time Adaptation: An Investigation into Realistic Test-Time Data Poisoning ICLR 2025