ResearchTrend.AI
VLMGuard: Defending VLMs against Malicious Prompts via Unlabeled Data

VLMGuard: Defending VLMs against Malicious Prompts via Unlabeled Data

Xuefeng Du
Reshmi Ghosh
Robert Sim
Ahmed Salem
Vitor Carvalho
Emily Lawton
Yixuan Li
Jack W. Stokes
ArXivPDFHTML

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

5 / 5 papers shown
Title
Safety in Large Reasoning Models: A Survey
Safety in Large Reasoning Models: A Survey
Cheng Wang
Y. Liu
B. Li
Duzhen Zhang
Z. Li
Junfeng Fang
LRM
91
1
0
24 Apr 2025
Safeguarding Vision-Language Models: Mitigating Vulnerabilities to Gaussian Noise in Perturbation-based Attacks
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
40
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
129
13
0
30 Jan 2025
Safety-Aware Fine-Tuning of Large Language Models
Safety-Aware Fine-Tuning of Large Language Models
Hyeong Kyu Choi
Xuefeng Du
Yixuan Li
35
11
0
13 Oct 2024
HaloScope: Harnessing Unlabeled LLM Generations for Hallucination Detection
HaloScope: Harnessing Unlabeled LLM Generations for Hallucination Detection
Xuefeng Du
Chaowei Xiao
Yixuan Li
HILM
29
16
0
26 Sep 2024