Adversarial Learning

PBCAT: Patch-Based Composite Adversarial Training against Physically Realizable Attacks on Object Detection ICCV 2025 PBI-Attack: Prior-Guided Bimodal Interactive Black-Box Jailbreak Attack for Toxicity Maximization EMNLP 2025 People who frequently use ChatGPT for writing tasks are accurate and robust detectors of AI-generated text ACL 2025 Perception-Guided Jailbreak Against Text-to-Image Models AAAI 2025 PerReactor: Offline Personalised Multiple Appropriate Facial Reaction Generation AAAI 2025 Ph-GAN: Physics-Inspired GAN for Generating SAR Images Under Limited Data ICCV 2025 PhyCamo: A Robust Physical Camouflage via Contrastive Learning for Multi-View Physical Adversarial Attack AAAI 2025 PIG: Privacy Jailbreak Attack on LLMs via Gradient-based Iterative In-Context Optimization ACL 2025 Pixel Is Not a Barrier: An Effective Evasion Attack for Pixel-Domain Diffusion Models AAAI 2025 PLA: Prompt Learning Attack against Text-to-Image Generative Models ICCV 2025 PoolAtnRes: Towards Generalisable Differential Morphing Attack Detection WACV 2025 PopAlign: Diversifying Contrasting Patterns for a More Comprehensive Alignment ACL 2025 Power of Diversity: Enhancing Data-Free Black-Box Attack with Domain-Augmented Learning AAAI 2025 PRDetect: Perturbation-Robust LLM-generated Text Detection Based on Syntax Tree NAACL 2025 Precision vs. Perturbation: Robustness Analysis of Synonym Attacks in Ukrainian NLP ACL 2025 Pretend Benign: A Stealthy Adversarial Attack by Exploiting Vulnerabilities in Cooperative Perception ICCV 2025 Protecting Model Adaptation from Trojans in the Unlabeled Data AAAI 2025 PsyScam: A Benchmark for Psychological Techniques in Real-World Scams EMNLP 2025 Q-FAKER: Query-free Hard Black-box Attack via Controlled Generation NAACL 2025 R2S: Real-to-Synthetic Representation Learning for Training Speech Recognition Models on Synthetic Data Interspeech 2025 RapFlow-TTS: Rapid and High-Fidelity Text-to-Speech with Improved Consistency Flow Matching Interspeech 2025 Real-Time Neural Denoising with Render-Aware Knowledge Distillation AAAI 2025 Reducing the Content Bias for AI-Generated Image Detection WACV 2025 Refusal-Aware Red Teaming: Exposing Inconsistency in Safety Evaluations EMNLP 2025 Reimagining Safety Alignment with An Image EMNLP 2025