conftrace_

harmful content

66 papers

Explore in graph

Co-occurring keywords

large language model (13587) jailbreak attack (225) safety alignment (178) adversarial attack (1621) model alignment (226) safety evaluation (94) llm safety (67) ai safety (235) model safety (101) adversarial learning (1595)

Papers

WALKSAFE: Risk-aware Graph Random Walk with Bi-GRPO for LLM Safety AAAI 2026
HumorReject: Decoupling LLM Safety from Refusal Prefix via a Little Humor AAAI 2026
Mass Concept Erasure in Diffusion Models with Concept Hierarchy AAAI 2026
Engagement Undermines Safety: How Stereotypes and Toxicity Shape Humor in Language Models EACL 2026
What Are They Filtering Out? An Experimental Benchmark of Filtering Strategies for Harm Reduction in Pretraining Datasets AAAI 2026
Thesis Proposal: An Explainable Multimodal Framework for Detecting Harmful Content in Code-Switched Children’s Media ACL 2026
Safe in Isolation, Dangerous Together: Agent-Driven Multi-Turn Decomposition Jailbreaks on LLMs ACL 2025
Intrinsic Model Weaknesses: How Priming Attacks Unveil Vulnerabilities in Large Language Models NAACL 2025
Re-ranking Using Large Language Models for Mitigating Exposure to Harmful Content on Social Media Platforms ACL 2025
SafetyQuizzer: Timely and Dynamic Evaluation on the Safety of LLMs NAACL 2025
Visual Contextual Attack: Jailbreaking MLLMs with Image-Driven Context Injection EMNLP 2025
Six-CD: Benchmarking Concept Removals for Text-to-image Diffusion Models CVPR 2025
Token-Aware Editing of Internal Activations for Large Language Model Alignment EMNLP 2025
Learn and Unlearn: Addressing Misinformation in Multilingual LLMs EMNLP 2025
Safety Alignment via Constrained Knowledge Unlearning ACL 2025
Shaping the Safety Boundaries: Understanding and Defending Against Jailbreaks in Large Language Models ACL 2025
Are Vision-Language Models Safe in the Wild? A Meme-Based Benchmark Study EMNLP 2025
Harmful Prompt Laundering: Jailbreaking LLMs with Abductive Styles and Symbolic Encoding EMNLP 2025
How to Fine-Tune Safely on a Budget: Model Adaptation Using Minimal Resources EMNLP 2025
Look Before You Leap: Enhance Attention and Vigilance Regarding Harmful Content with GuidelineLLM AAAI 2025
Internal Activation Revision: Safeguarding Vision Language Models Without Parameter Update AAAI 2025
RTP-LX: Can LLMs Evaluate Toxicity in Multilingual Scenarios? AAAI 2025
AlignGuard: Scalable Safety Alignment for Text-to-Image Generation ICCV 2025
WordGame: Efficient & Effective LLM Jailbreak via Simultaneous Obfuscation in Query and Response NAACL 2025
TRIDENT: Enhancing Large Language Model Safety with Tri-Dimensional Diversified Red-Teaming Data Synthesis ACL 2025