Adversarial Learning

Iron Sharpens Iron: Defending Against Attacks in Machine-Generated Text Detection with Adversarial Training ACL 2025 Is Poisoning a Real Threat to DPO? Maybe More So Than You Think AAAI 2025 Is your benchmark truly adversarial? AdvScore: Evaluating Human-Grounded Adversarialness NAACL 2025 Iterative Nash Policy Optimization: Aligning LLMs with General Preferences via No-Regret Learning ICLR 2025 IterComp: Iterative Composition-Aware Feedback Learning from Model Gallery for Text-to-Image Generation ICLR 2025 Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks ICLR 2025 Jailbreaking? One Step Is Enough! ACL 2025 Jailbreaking Prompt Attack: A Controllable Adversarial Attack against Diffusion Models NAACL 2025 Jailbreaking the Non-Transferable Barrier via Test-Time Data Disguising CVPR 2025 Jailbreaking with Universal Multi-Prompts NAACL 2025 Jailbreak LLMs through Internal Stance Manipulation EMNLP 2025 Jailbreak-Tuning: Models Efficiently Learn Jailbreak Susceptibility EMNLP 2025 JailPO: A Novel Black-Box Jailbreak Framework via Preference Optimization Against Aligned LLMs AAAI 2025 KDAT: Inherent Adversarial Robustness via Knowledge Distillation with Adversarial Tuning for Object Detection Models AAAI 2025 Kill two birds with one stone: generalized and robust AI-generated text detection via dynamic perturbations NAACL 2025 KOEnsAttack: Towards Efficient Data-Free Black-Box Adversarial Attacks via Knowledge-Orthogonalized Substitute Ensembles ICCV 2025 Label-Free Backdoor Attacks in Vertical Federated Learning AAAI 2025 Language Models May Verbatim Complete Text They Were Not Explicitly Trained On ICML 2025 Large Learning Rates Simultaneously Achieve Robustness to Spurious Correlations and Compressibility ICCV 2025 Learning Counterfactually Decoupled Attention for Open-World Model Attribution ICCV 2025 Learning Diverse Attacks on Large Language Models for Robust Red-Teaming and Safety Tuning ICLR 2025 Learning from Mistakes: Self-correct Adversarial Training for Chinese Unnatural Text Correction AAAI 2025 Learning Optimal Auctions with Correlated Value Distributions AAAI 2025 Learning Robust and Privacy-Preserving Representations via Information Theory AAAI 2025 Learning to Incentivize in Repeated Principal-Agent Problems with Adversarial Agent Arrivals ICML 2025