safety alignment

iMotion-LLM: Instruction-Conditioned Trajectory Generation WACV 2026 In-Context Representation Hijacking ACL 2026 IndicJR: A Judge-Free Benchmark of Jailbreak Robustness in South Asian Languages EACL 2026 Interpretable Safety Alignment via SAE-Constructed Low-Rank Subspace Adaptation ACL 2026 Jailbreaking Multimodal Large Language Models using Multi-Clip Video ACL 2026 Jailbreaking Vision-Language Models via Dissonance-Guided Suffix Optimization and Image-Phrase Injection CVPR 2026 Jailbreaks as Inference-Time Alignment: A Framework for Understanding Safety Failures in LLMs EACL 2026 Jailbreak-Zero: A Path to Pareto Optimal Red Teaming for Large Language Models ACL 2026 JPU: Bridging Jailbreak Defense and Unlearning via On-Policy Path Rectification ACL 2026 LASA: Language-Agnostic Semantic Alignment at the Semantic Bottleneck for LLM Safety ACL 2026 Layer-wise Swapping for Generalizable Multilingual Safety EACL 2026 LLM-VA: Resolving the Jailbreak-Overrefusal Trade-off via Vector Alignment ACL 2026 Mitigating Over-Refusal in Aligned Large Language Models via Inference-Time Activation Energy ACL 2026 More Thinking, Less Talking: Internalizing Deliberative Safety into LLM Parameters ACL 2026 OASIS: Mitigating Harmful Fine-tuning Attacks on LLMs via Orthogonal and Adaptive Safety Alignment Strategy ACL 2026 Please refuse to answer me! Mitigating Over-Refusal in Large Language Models via Adaptive Contrastive Decoding ACL 2026 Probing the Safety Robustness of LLMs in Latent Space ACL 2026 Reasoning Structure Matters for Safety Alignment of Reasoning Models ACL 2026 Resolving the Security-Auditability Dilemma with Auditable Latent Chain-of-Thought Alignment ACL 2026 Rethinking Deep Alignment Through the Lens of Incomplete Safety Learning AAAI 2026 Safeguarding LLM Fine-tuning via Push-Pull Distributional Alignment ACL 2026 SafeLogo: Turning Your Logos into Jailbreak Shields via Micro-Regional Adversarial Training CVPR 2026 Safety Alignment of Large Language Models via Contrasting Safe and Harmful Distributions AAAI 2026 Safety-Utility Conflicts Are Not Global: Surgical Alignment via Head-Level Diagnosis ACL 2026 Seeing No Evil: Blinding Large Vision-Language Models to Safety Instructions via Adversarial Attention Hijacking ACL 2026