conftrace_

unsafe content

9 papers

Explore in graph

Co-occurring keywords · papers mentioning both

large language model (4) jailbreak attack (3) unsafe content detection (2) vision-language model (2) text-to-image model (2) arabic transliteration (1) output safety (1) entailment hierarchy (1) prompt manipulation (1) safety refusal (1)

Papers

Safe Vision-Language Models via Unsafe Weights Manipulation WACV 2026 ShieldRAG: Safeguarding Retrieval-Augmented Generation from Untrusted Knowledge Bases AAAI 2026 Hyperbolic Safety-Aware Vision-Language Models CVPR 2025 Multimodal Pragmatic Jailbreak on Text-to-image Models ACL 2025 Perception-Guided Jailbreak Against Text-to-Image Models AAAI 2025 SecDecoding: Steerable Decoding for Safer LLM Generation EMNLP 2025 SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal ICLR 2025 Jailbreaking LLMs with Arabic Transliteration and Arabizi EMNLP 2024 Learning and Forgetting Unsafe Examples in Large Language Models ICML 2024