Adversarial Learning

Keeping up with dynamic attackers: Certifying robustness to adaptive online data poisoning AISTATS 2025 KOEnsAttack: Towards Efficient Data-Free Black-Box Adversarial Attacks via Knowledge-Orthogonalized Substitute Ensembles ICCV 2025 Label-Perceptive Adversarial Domain Adaptation for Named Entity Recognition in Traditional Chinese Medicine: Dataset and Approach ACML 2025 Learning to Sample in Stochastic Optimization UAI 2025 Leveraging Spatial Invariance to Boost Adversarial Transferability ICCV 2025 LlmFixer: Fix the Helpfulness of Defensive Large Language Models EMNLP 2025 LLMs Caught in the Crossfire: Malware Requests and Jailbreak Challenges ACL 2025 LLMs know their vulnerabilities: Uncover Safety Gaps through Natural Distribution Shifts ACL 2025 Low-Frequency Black-Box Backdoor Attack via Evolutionary Algorithm WACV 2025 M2S: Multi-turn to Single-turn jailbreak in Red Teaming for LLMs ACL 2025 Making Every Step Effective: Jailbreaking Large Vision-Language Models Through Hierarchical KV Equalization EMNLP 2025 MalCL: Leveraging GAN-Based Generative Replay to Combat Catastrophic Forgetting in Malware Classification AAAI 2025 Masks and Mimicry: Strategic Obfuscation and Impersonation Attacks on Authorship Verification NAACL 2025 Membership Inference Attacks with False Discovery Rate Control ICCV 2025 Meme Trojan: Backdoor Attacks Against Hateful Meme Detection via Cross-Modal Triggers AAAI 2025 Mimic Blocker: Self-Supervised Adversarial Training for Voice Conversion Defense with Pretrained Feature Extractors Interspeech 2025 Mind the Cost of Scaffold! Benign Clients May Even Become Accomplices of Backdoor Attack ICCV 2025 Mind the Gap: Detecting Black-box Adversarial Attacks in the Making through Query Update Analysis CVPR 2025 Mind the Trojan Horse: Image Prompt Adapter Enabling Scalable and Deceptive Jailbreaking CVPR 2025 Misalignment Attack on Text-to-Image Models via Text Embedding Optimization and Inversion EMNLP 2025 Mitigating Catastrophic Overfitting in Fast Adversarial Training via Label Information Elimination ICCV 2025 Mitigating Feature Gap for Adversarial Robustness by Feature Disentanglement AAAI 2025 Model Poisoning Attacks to Federated Learning via Multi-Round Consistency CVPR 2025 MOS-Attack: A Scalable Multi-objective Adversarial Attack Framework CVPR 2025 MULBERE: Multilingual Jailbreak Robustness Using Targeted Latent Adversarial Training EMNLP 2025