VLMGuard: Defending VLMs against Malicious Prompts via Unlabeled Data

VLMGuard: Defending VLMs against Malicious Prompts via Unlabeled Data

1 October 2024

Ahmed Salem

Yixuan Li

Papers citing "VLMGuard: Defending VLMs against Malicious Prompts via Unlabeled Data"

5 / 5 papers shown

Title
Safety in Large Reasoning Models: A Survey Cheng Wang Y. Liu B. Li Duzhen Zhang Z. Li Junfeng Fang LRM 44 1 0 24 Apr 2025
Safeguarding Vision-Language Models: Mitigating Vulnerabilities to Gaussian Noise in Perturbation-based Attacks Jiawei Wang Yushen Zuo Yuanjun Chai Z. Liu Yichen Fu Yichun Feng Kin-Man Lam AAML VLM 34 0 0 02 Apr 2025
GuardReasoner: Towards Reasoning-based LLM Safeguards Yue Liu Hongcheng Gao Shengfang Zhai Jun-Xiong Xia Tianyi Wu Zhiwei Xue Y. Chen Kenji Kawaguchi Jiaheng Zhang Bryan Hooi AI4TS LRM 106 13 0 30 Jan 2025
Safety-Aware Fine-Tuning of Large Language Models Hyeong Kyu Choi Xuefeng Du Yixuan Li 32 10 0 13 Oct 2024
HaloScope: Harnessing Unlabeled LLM Generations for Hallucination Detection Xuefeng Du Chaowei Xiao Yixuan Li HILM 19 16 0 26 Sep 2024