Adversarial Learning

Provably Mitigating Overoptimization in RLHF: Your SFT Loss is Implicitly an Adversarial Regularizer NeurIPS 2024 PRP: Propagating Universal Perturbations to Attack Large Language Model Guard-Rails ACL 2024 Pseudo-Private Data Guided Model Inversion Attacks NeurIPS 2024 Putting Gale & Shapley to Work: Guaranteeing Stability Through Learning NeurIPS 2024 Query-Based Adversarial Prompt Generation NeurIPS 2024 Query-Efficient Textual Adversarial Example Generation for Black-Box Attacks NAACL 2024 R.A.C.E.: Robust Adversarial Concept Erasure for Secure Text-to-Image Diffusion Model ECCV 2024 RAFT: Realistic Attacks to Fool Text Detectors EMNLP 2024 Rainbow Teaming: Open-Ended Generation of Diverse Adversarial Prompts NeurIPS 2024 RAMP: Boosting Adversarial Robustness Against Multiple l_p Perturbations for Universal Robustness NeurIPS 2024 Random Entangled Tokens for Adversarially Robust Vision Transformer CVPR 2024 Randomized Adversarial Style Perturbations for Domain Generalization WACV 2024 Ranking Manipulation for Conversational Search Engines EMNLP 2024 Rapid Plug-in Defenders NeurIPS 2024 RAt: Injecting Implicit Bias for Text-To-Image Prompt Refinement Models EMNLP 2024 RAUCA: A Novel Physical Adversarial Attack on Vehicle Detectors via Robust and Accurate Camouflage Generation ICML 2024 RAW: A Robust and Agile Plug-and-Play Watermark Framework for AI-Generated Images with Provable Guarantees NeurIPS 2024 READ: Improving Relation Extraction from an ADversarial Perspective NAACL 2024 ReEval: Automatic Hallucination Evaluation for Retrieval-Augmented Large Language Models via Transferable Adversarial Attacks NAACL 2024 Reimagining Mutual Information for Enhanced Defense against Data Leakage in Collaborative Inference NeurIPS 2024 Releasing the Capacity of GANs in Non-Autoregressive Image Captioning COLING 2024 Representation Alignment and Adversarial Networks for Cross-lingual Dependency Parsing EMNLP 2024 Representation-Based Robustness in Goal-Conditioned Reinforcement Learning AAAI 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