Adversarial Learning

Robust Safety Classifier Against Jailbreaking Attacks: Adversarial Prompt Shield NAACL 2024 Sandwich attack: Multi-language Mixture Adaptive Attack on LLMs NAACL 2024 Securing Multi-turn Conversational Language Models From Distributed Backdoor Attacks EMNLP 2024 SEER: Backdoor Detection for Vision-Language Models through Searching Target Text and Image Trigger Jointly AAAI 2024 Semantic-Aware Multi-Label Adversarial Attacks CVPR 2024 Shadowcast: Stealthy Data Poisoning Attacks Against Vision-Language Models NeurIPS 2024 Shortcuts Arising from Contrast: Towards Effective and Lightweight Clean-Label Attacks in Prompt-Based Learning EMNLP 2024 SleeperNets: Universal Backdoor Poisoning Attacks Against Reinforcement Learning Agents NeurIPS 2024 SlowFormer: Adversarial Attack on Compute and Energy Consumption of Efficient Vision Transformers CVPR 2024 Spear: Evaluate the Adversarial Robustness of Compressed Neural Models IJCAI 2024 Spectrum Extraction and Clipping for Implicitly Linear Layers AISTATS 2024 SpeechGuard: Exploring the Adversarial Robustness of Multi-modal Large Language Models ACL 2024 TARP-VP: Towards Evaluation of Transferred Adversarial Robustness and Privacy on Label Mapping Visual Prompting Models NeurIPS 2024 Taxonomy Driven Fast Adversarial Training AAAI 2024 Temporal-Distributed Backdoor Attack against Video Based Action Recognition AAAI 2024 The Best Defense is Attack: Repairing Semantics in Textual Adversarial Examples EMNLP 2024 The data-driven transferable adversarial space ACML 2024 The Implicit Bias of Gradient Descent toward Collaboration between Layers: A Dynamic Analysis of Multilayer Perceptions NeurIPS 2024 The Lipschitz-Variance-Margin Tradeoff for Enhanced Randomized Smoothing ICLR 2024 The Price of Implicit Bias in Adversarially Robust Generalization NeurIPS 2024 Towards Accurate and Robust Architectures via Neural Architecture Search CVPR 2024 Towards Large Certified Radius in Randomized Smoothing Using Quasiconcave Optimization AAAI 2024 Towards Transferable Adversarial Attacks with Centralized Perturbation AAAI 2024 Towards Transferable Targeted 3D Adversarial Attack in the Physical World CVPR 2024 Towards Understanding Jailbreak Attacks in LLMs: A Representation Space Analysis EMNLP 2024