harmful output

ShieldRAG: Safeguarding Retrieval-Augmented Generation from Untrusted Knowledge Bases AAAI 2026 Cannot See the Forest for the Trees: Invoking Heuristics and Biases to Elicit Irrational Choices of LLMs ICML 2025 ELITE: Enhanced Language-Image Toxicity Evaluation for Safety ICML 2025 Investigating the Security Threat Arising from “Yes-No” Implicit Bias in Large Language Models AAAI 2025 ProAdvPrompter: A Two-Stage Journey to Effective Adversarial Prompting for LLMs ICLR 2025 Root Defense Strategies: Ensuring Safety of LLM at the Decoding Level ACL 2025 Single Character Perturbations Break LLM Alignment AAAI 2025 Improving Alignment and Robustness with Circuit Breakers NeurIPS 2024 Large Language Models Are Involuntary Truth-Tellers: Exploiting Fallacy Failure for Jailbreak Attacks EMNLP 2024 Removing RLHF Protections in GPT-4 via Fine-Tuning NAACL 2024 On Second Thought, Let’s Not Think Step by Step! Bias and Toxicity in Zero-Shot Reasoning ACL 2023 Unveiling Safety Vulnerabilities of Large Language Models EMNLP 2023