conftrace_

model safety

111 papers

Explore in graph

Co-occurring keywords · papers mentioning both

large language model (63) jailbreak attack (20) adversarial attack (18) safety alignment (16) ai safety (9) jailbreak defense (9) adversarial robustness (9) adversarial learning (9) language model (8) harmful content (7)

Papers

Truth, Trust, and Trouble: Medical AI on the Edge EMNLP 2025 Unintentional Unalignment: Likelihood Displacement in Direct Preference Optimization ICLR 2025 Unraveling the Mystery: Defending Against Jailbreak Attacks Via Unearthing Real Intention COLING 2025 UnsafeChain: Enhancing Reasoning Model Safety via Hard Cases IJCNLP 2025 VSCBench: Bridging the Gap in Vision-Language Model Safety Calibration ACL 2025 What Features in Prompts Jailbreak LLMs? Investigating the Mechanisms Behind Attacks EMNLP 2025 Aligners: Decoupling LLMs and Alignment EMNLP 2024 Alignment-Enhanced Decoding: Defending Jailbreaks via Token-Level Adaptive Refining of Probability Distributions EMNLP 2024 Bag of Tricks: Benchmarking of Jailbreak Attacks on LLMs NeurIPS 2024 Data-Driven Discovery of Design Specifications (Student Abstract) AAAI 2024 Defending Large Language Models Against Jailbreak Attacks via Layer-specific Editing EMNLP 2024 Direct Unlearning Optimization for Robust and Safe Text-to-Image Models NeurIPS 2024 Down the Toxicity Rabbit Hole: A Framework to Bias Audit Large Language Models with Key Emphasis on Racism, Antisemitism, and Misogyny IJCAI 2024 Evaluating Psychological Safety of Large Language Models EMNLP 2024 Fight Back Against Jailbreaking via Prompt Adversarial Tuning NeurIPS 2024 Fishing for Magikarp: Automatically Detecting Under-trained Tokens in Large Language Models EMNLP 2024 Gaining Wisdom from Setbacks: Aligning Large Language Models via Mistake Analysis ICLR 2024 Immunization against harmful fine-tuning attacks EMNLP 2024 InferAligner: Inference-Time Alignment for Harmlessness through Cross-Model Guidance EMNLP 2024 Large Language Models Are Involuntary Truth-Tellers: Exploiting Fallacy Failure for Jailbreak Attacks EMNLP 2024 Large Language Models Relearn Removed Concepts ACL 2024 Making Harmful Behaviors Unlearnable for Large Language Models ACL 2024 Navigating the OverKill in Large Language Models ACL 2024 Rainbow Teaming: Open-Ended Generation of Diverse Adversarial Prompts NeurIPS 2024 Removing RLHF Protections in GPT-4 via Fine-Tuning NAACL 2024