adversarial defense

MLLM-Protector: Ensuring MLLM’s Safety without Hurting Performance EMNLP 2024 MMCert: Provable Defense against Adversarial Attacks to Multi-modal Models CVPR 2024 Modeling Aspect Sentiment Coherency via Local Sentiment Aggregation EACL 2024 Model Inversion Robustness: Can Transfer Learning Help? CVPR 2024 MoGU: A Framework for Enhancing Safety of LLMs While Preserving Their Usability NeurIPS 2024 NCIS: Neural Contextual Iterative Smoothing for Purifying Adversarial Perturbations WACV 2024 Nearest is Not Dearest: Towards Practical Defense against Quantization-conditioned Backdoor Attacks CVPR 2024 Optimal Zero-Shot Detector for Multi-Armed Attacks AISTATS 2024 ORTicket: Let One Robust BERT Ticket Transfer across Different Tasks COLING 2024 PAD: Patch-Agnostic Defense against Adversarial Patch Attacks CVPR 2024 PointCVaR: Risk-Optimized Outlier Removal for Robust 3D Point Cloud Classification AAAI 2024 Progressive Poisoned Data Isolation for Training-Time Backdoor Defense AAAI 2024 Protecting Object Detection Models from Model Extraction Attack via Feature Space Coverage IJCAI 2024 Random Entangled Tokens for Adversarially Robust Vision Transformer CVPR 2024 Representation Noising: A Defence Mechanism Against Harmful Finetuning NeurIPS 2024 Resisting Backdoor Attacks in Federated Learning via Bidirectional Elections and Individual Perspective AAAI 2024 Revisiting Adversarial Training Under Long-Tailed Distributions CVPR 2024 Robust Prompt Optimization for Defending Language Models Against Jailbreaking Attacks NeurIPS 2024 SAME: Sample Reconstruction against Model Extraction Attacks AAAI 2024 Spear and Shield: Adversarial Attacks and Defense Methods for Model-Based Link Prediction on Continuous-Time Dynamic Graphs AAAI 2024 Subspace Defense: Discarding Adversarial Perturbations by Learning a Subspace for Clean Signals COLING 2024 Textual-Driven Adversarial Purification for Speaker Verification Interspeech 2024 The Best Defense is Attack: Repairing Semantics in Textual Adversarial Examples EMNLP 2024 Trap-MID: Trapdoor-based Defense against Model Inversion Attacks NeurIPS 2024 Two Heads are Better than One: Nested PoE for Robust Defense Against Multi-Backdoors NAACL 2024