attack success rate

Activation-Guided Local Editing for Jailbreaking Attacks ACL 2026 AdapAction: Adaptive Target Action Backdoor Attack against GUI Agents CVPR 2026 Are My Optimized Prompts Compromised? Exploring Vulnerabilities of LLM-based Optimizers EACL 2026 Backdoor Collapse: Eliminating Unknown Threats Via Known Backdoor Aggregation In Language Models ACL 2026 Between a Rock and a Hard Place: The Tension Between Ethical Reasoning and Safety Alignment in LLMs ACL 2026 Enhancing the Transferability of Jailbreak Attacks on Large Language Models via Exploiting Reparameterization Invariance ACL 2026 HarmRLVR: Weaponizing Verifiable Rewards for Harmful LLM Alignment ACL 2026 Hierarchical Attacks for Multi-Modal Multi-Agent Reasoning CVPR 2026 LASA: Language-Agnostic Semantic Alignment at the Semantic Bottleneck for LLM Safety ACL 2026 MAJIC: Markovian Adaptive Jailbreaking via Iterative Composition of Diverse Innovative Strategies AAAI 2026 More Thinking, Less Talking: Internalizing Deliberative Safety into LLM Parameters ACL 2026 Principled Steering via Null-space Projection for Jailbreak Defense in Vision-Language Models CVPR 2026 RaPA: Enhancing Transferable Targeted Attacks via Random Parameter Pruning CVPR 2026 SafeMT: Multi-turn Safety for Multimodal Language Models ACL 2026 ShadeEdit: A Utility-Preserving and Defense-Evasive Knowledge Manipulation Attack in Federated LLMs AAAI 2026 The Side Effects of Being Smart: Safety Risks in MLLMs’ Multi-Image Reasoning ACL 2026 TreeTeaming: Autonomous Red-Teaming of Vision-Language Models via Hierarchical Strategy Exploration CVPR 2026 V-Attack: Targeting Disentangled Value Features for Controllable Adversarial Attacks on LVLMs CVPR 2026 When Personalization Legitimizes Risks: Uncovering Safety Vulnerabilities in Personalized Dialogue Agents ACL 2026 Adversarial Attacks on Text-dependent Speaker Verification System Interspeech 2025 An Optimizable Suffix Is Worth A Thousand Templates: Efficient Black-box Jailbreaking without Affirmative Phrases via LLM as Optimizer NAACL 2025 ASTPrompter: Preference-Aligned Automated Language Model Red-Teaming to Generate Low-Perplexity Unsafe Prompts EMNLP 2025 CL-Attack: Textual Backdoor Attacks via Cross-Lingual Triggers AAAI 2025 Defending LVLMs Against Vision Attacks Through Partial-Perception Supervision ICML 2025 Defense against Prompt Injection Attacks via Mixture of Encodings NAACL 2025