English
Related papers

Related papers: RapGuard: Safeguarding Multimodal Large Language M…

200 papers

We introduce Llama Guard 3 Vision, a multimodal LLM-based safeguard for human-AI conversations that involves image understanding: it can be used to safeguard content for both multimodal LLM inputs (prompt classification) and outputs…

Computer Vision and Pattern Recognition · Computer Science 2024-11-18 Jianfeng Chi , Ujjwal Karn , Hongyuan Zhan , Eric Smith , Javier Rando , Yiming Zhang , Kate Plawiak , Zacharie Delpierre Coudert , Kartikeya Upasani , Mahesh Pasupuleti

Large Language Models (LLMs) are typically aligned for safety during the post-training phase; however, they may still generate inappropriate outputs that could potentially pose risks to users. This challenge underscores the need for robust…

Machine Learning · Computer Science 2025-12-08 Mahesh Kumar Nandwana , Youngwan Lim , Joseph Liu , Alex Yang , Varun Notibala , Nishchaie Khanna

Prepending model inputs with safety prompts is a common practice for safeguarding large language models (LLMs) against queries with harmful intents. However, the underlying working mechanisms of safety prompts have not been unraveled yet,…

Machine Learning · Computer Science 2024-06-04 Chujie Zheng , Fan Yin , Hao Zhou , Fandong Meng , Jie Zhou , Kai-Wei Chang , Minlie Huang , Nanyun Peng

Large language models (LLMs) excel in diverse applications but face dual challenges: generating harmful content under jailbreak attacks and over-refusal of benign queries due to rigid safety mechanisms. These issues are further complicated…

Artificial Intelligence · Computer Science 2025-11-04 Yifan Xia , Guorui Chen , Wenqian Yu , Zhijiang Li , Philip Torr , Jindong Gu

Multimodal large reasoning models (MLRMs) are increasingly deployed for vision-language tasks that produce explicit intermediate rationales. However, reasoning traces can contain unsafe content even when the final answer is non-harmful,…

Computer Vision and Pattern Recognition · Computer Science 2025-11-27 Yuxiao Xiang , Junchi Chen , Zhenchao Jin , Changtao Miao , Haojie Yuan , Qi Chu , Tao Gong , Nenghai Yu

Large Language Models (LLMs) have rapidly become integral to numerous applications in critical domains where reliability is paramount. Despite significant advances in safety frameworks and guardrails, current protective measures exhibit…

Cryptography and Security · Computer Science 2025-04-15 Bibek Upadhayay , Vahid Behzadan , Ph. D

Vision-Language Models (VLMs) have achieved remarkable progress in multimodal reasoning tasks through enhanced chain-of-thought capabilities. However, this advancement also introduces novel safety risks, as these models become increasingly…

Computer Vision and Pattern Recognition · Computer Science 2025-10-22 Yinan Xia , Yilei Jiang , Yingshui Tan , Xiaoyong Zhu , Xiangyu Yue , Bo Zheng

Maintaining the safety of large language models (LLMs) is crucial as they are increasingly deployed in real-world applications. Existing safety guardrails typically rely on single-pass classification or, more recently, distilled reasoning.…

Artificial Intelligence · Computer Science 2026-05-29 Siddharth Sai , Xiaofei Wen , Muhao Chen

The increasing deployment of Large Language Models (LLMs) across enterprise and mission-critical domains has underscored the urgent need for robust guardrailing systems that ensure safety, reliability, and compliance. Existing solutions…

Computation and Language · Computer Science 2025-10-16 Karthik Avinash , Nikhil Pareek , Rishav Hada

Large language models (LLMs) are susceptible to red teaming attacks, which can induce LLMs to generate harmful content. Previous research constructs attack prompts via manual or automatic methods, which have their own limitations on…

Computation and Language · Computer Science 2023-10-20 Boyi Deng , Wenjie Wang , Fuli Feng , Yang Deng , Qifan Wang , Xiangnan He

Memory-augmented large language models extend reasoning beyond a fixed context window by maintaining long-term memory across interactions. However, existing memory systems often collapse stable user facts, episodic events, and behavioral…

Computation and Language · Computer Science 2026-05-28 Hyeonjeong Ha , Jeonghwan Kim , Cheng Qian , Jiayu Liu , William M. Campbell , Yue Wu , Yuji Zhang , Kathleen McKeown , Dilek Hakkani-Tur , Heng Ji

Tool-augmented Large Language Model (LLM) agents have demonstrated impressive capabilities in automating complex, multi-step real-world tasks, yet remain vulnerable to indirect prompt injection. Adversaries exploit this weakness by…

Cryptography and Security · Computer Science 2026-05-12 Wei Zhao , Zhe Li , Peixin Zhang , Jun Sun

Large language models (LLMs) have demonstrated immense utility across various industries. However, as LLMs advance, the risk of harmful outputs increases due to incorrect or malicious instruction prompts. While current methods effectively…

Computation and Language · Computer Science 2025-06-19 Xinyi Zeng , Yuying Shang , Jiawei Chen , Jingyuan Zhang , Yu Tian

Vision-language models (VLMs) are essential for contextual understanding of both visual and textual information. However, their vulnerability to adversarially manipulated inputs presents significant risks, leading to compromised outputs and…

Machine Learning · Computer Science 2024-10-02 Xuefeng Du , Reshmi Ghosh , Robert Sim , Ahmed Salem , Vitor Carvalho , Emily Lawton , Yixuan Li , Jack W. Stokes

The increasing sophistication of large vision-language models (LVLMs) has been accompanied by advances in safety alignment mechanisms designed to prevent harmful content generation. However, these defenses remain vulnerable to sophisticated…

Cryptography and Security · Computer Science 2026-04-09 Quanchen Zou , Zonghao Ying , Moyang Chen , Wenzhuo Xu , Yisong Xiao , Yakai Li , Deyue Zhang , Dongdong Yang , Zhao Liu , Xiangzheng Zhang

Large vision-language models (LVLMs) have achieved remarkable progress in vision-language reasoning tasks, yet ensuring their safety remains a critical challenge. Recent input-side defenses detect unsafe images with CLIP and prepend safety…

Computer Vision and Pattern Recognition · Computer Science 2026-03-02 Xingyu Zhu , Beier Zhu , Junfeng Fang , Shuo Wang , Yin Zhang , Xiang Wang , Xiangnan He

Multimodal Large Reasoning Models (MLRMs) demonstrate impressive cross-modal reasoning but often amplify safety risks under adversarial or unsafe prompts, a phenomenon we call the \textit{Reasoning Tax}. Existing defenses mainly act at the…

Machine Learning · Computer Science 2025-10-10 Huahui Yi , Kun Wang , Qiankun Li , Miao Yu , Liang Lin , Gongli Xi , Hao Wu , Xuming Hu , Kang Li , Yang Liu

The rapid development of Multimodal Large Reasoning Models (MLRMs) has demonstrated broad application potential, yet their safety and reliability remain critical concerns that require systematic exploration. To address this gap, we conduct…

Computation and Language · Computer Science 2025-10-14 Xinyue Lou , You Li , Jinan Xu , Xiangyu Shi , Chi Chen , Kaiyu Huang

Large Vision-Language Models (LVLMs) unlock powerful multimodal reasoning but also expand the attack surface, particularly through adversarial inputs that conceal harmful goals in benign prompts. We propose SHIELD, a lightweight,…

Computation and Language · Computer Science 2025-10-16 Juan Ren , Mark Dras , Usman Naseem

Multimodal large language models (MLLMs) are gaining increasing attention. Due to the heterogeneity of their input features, they face significant challenges in terms of jailbreak defenses. Current defense methods rely on costly fine-tuning…

Artificial Intelligence · Computer Science 2026-05-13 Xinyi Zeng , Xue Yang , Jingyuan Zhang , Huanqian Yan , Xiang Chen , Kaiwen Wei , Hankun Kang , Yu Tian