Adversarial Learning

System Prompt Hijacking via Permutation Triggers in LLM Supply Chains ACL 2025 Temporal Unlearnable Examples: Preventing Personal Video Data from Unauthorized Exploitation by Object Tracking ICCV 2025 TempParaphraser: “Heating Up” Text to Evade AI-Text Detection through Paraphrasing EMNLP 2025 Test-Time Backdoor Detection for Object Detection Models CVPR 2025 The Dangers of Indirect Prompt Injection Attacks on LLM-based Autonomous Web Navigation Agents: A Demonstration EMNLP 2025 The Great Contradiction Showdown: How Jailbreak and Stealth Wrestle in Vision-Language Models? ACML 2025 The TIP of the Iceberg: Revealing a Hidden Class of Task-in-Prompt Adversarial Attacks on LLMs ACL 2025 TITAN: Query-Token based Domain Adaptive Adversarial Learning ICCV 2025 Token Highlighter: Inspecting and Mitigating Jailbreak Prompts for Large Language Models AAAI 2025 TombRaider: Entering the Vault of History to Jailbreak Large Language Models EMNLP 2025 Toward Optimal LLM Alignments Using Two-Player Games EMNLP 2025 Towards a 3D Transfer-based Black-box Attack via Critical Feature Guidance ICCV 2025 Towards Million-Scale Adversarial Robustness Evaluation With Stronger Individual Attacks CVPR 2025 Towards Optimal Branching of Linear and Semidefinite Relaxations for Neural Network Robustness Certification JMLR 2025 Towards Robust Defense against Customization via Protective Perturbation Resistant to Diffusion-based Purification ICCV 2025 Transferable Adversarial Face Attack with Text Controlled Attribute AAAI 2025 Transferable Direct Prompt Injection via Activation-Guided MCMC Sampling EMNLP 2025 TRNAS: A Training-Free Robust Neural Architecture Search ICCV 2025 TrojanWave: Exploiting Prompt Learning for Stealthy Backdoor Attacks on Large Audio-Language Models EMNLP 2025 Turning Logic Against Itself: Probing Model Defenses Through Contrastive Questions EMNLP 2025 Universal Acoustic Adversarial Attacks for Flexible Control of Speech-LLMs EMNLP 2025 Unveiling the Role of Randomization in Multiclass Adversarial Classification: Insights from Graph Theory AISTATS 2025 Using Humor to Bypass Safety Guardrails in Large Language Models ACL 2025 VisCRA: A Visual Chain Reasoning Attack for Jailbreaking Multimodal Large Language Models EMNLP 2025 Visual Contextual Attack: Jailbreaking MLLMs with Image-Driven Context Injection EMNLP 2025