English
Related papers

Related papers: GuardAlign: Test-time Safety Alignment in Multimod…

200 papers

Large Language Models (LLMs) are vulnerable to adversarial attacks that bypass safety guidelines and generate harmful content. Mitigating these vulnerabilities requires defense mechanisms that are both robust and computationally efficient.…

Machine Learning · Computer Science 2025-11-18 Gil Goren , Shahar Katz , Lior Wolf

Guard models are a critical component of LLM safety, but their sensitivity to superficial linguistic variations remains a key vulnerability. We show that even meaning-preserving paraphrases can cause large fluctuations in safety scores,…

Computation and Language · Computer Science 2025-11-17 Cristina Pinneri , Christos Louizos

Vision-language models (VLMs) are increasingly applied to identify unsafe or inappropriate images due to their internal ethical standards and powerful reasoning abilities. However, it is still unclear whether they can recognize various…

Cryptography and Security · Computer Science 2025-07-16 Yiting Qu , Michael Backes , Yang Zhang

Ensuring the safe alignment of large language models (LLMs) with human values is critical as they become integral to applications like translation and question answering. Current alignment methods struggle with dynamic user intentions and…

Computation and Language · Computer Science 2024-10-29 Rima Hazra , Sayan Layek , Somnath Banerjee , Soujanya Poria

Reinforcement learning (RL) has become a central post-training paradigm for large language models (LLMs), but its performance is highly sensitive to the quality of training problems. This sensitivity stems from the non-stationarity of RL:…

Machine Learning · Computer Science 2026-02-26 Ningyuan Yang , Weihua Du , Weiwei Sun , Sean Welleck , Yiming Yang

Current language model safety paradigms often fall short in emotionally charged or high-stakes settings, where refusal-only approaches may alienate users and naive compliance can amplify risk. We propose ProSocialAlign, a test-time,…

Computation and Language · Computer Science 2025-12-09 Somnath Banerjee , Sayan Layek , Sayantan Adak , Mykola Pechenizkiy , Animesh Mukherjee , Rima Hazra

Red-teaming has been a widely adopted way to evaluate the harmfulness of Large Language Models (LLMs). It aims to jailbreak a model's safety behavior to make it act as a helpful agent disregarding the harmfulness of the query. Existing…

Computation and Language · Computer Science 2023-11-14 Rishabh Bhardwaj , Soujanya Poria

With the rise of generative AI and rapid growth of high-quality video generation, video guardrails have become more crucial than ever to ensure safety and security across platforms. Current video guardrails, however, are either overly…

Computer Vision and Pattern Recognition · Computer Science 2024-12-11 Zhaorun Chen , Francesco Pinto , Minzhou Pan , Bo Li

Recent studies reveal that integrating new modalities into Large Language Models (LLMs), such as Vision-Language Models (VLMs), creates a new attack surface that bypasses existing safety training techniques like Supervised Fine-tuning (SFT)…

Computation and Language · Computer Science 2025-10-15 Trishna Chakraborty , Erfan Shayegani , Zikui Cai , Nael Abu-Ghazaleh , M. Salman Asif , Yue Dong , Amit K. Roy-Chowdhury , Chengyu Song

Vision language models (VLMs) extend the reasoning capabilities of large language models (LLMs) to cross-modal settings, yet remain highly vulnerable to multimodal jailbreak attacks. Existing defenses predominantly rely on safety…

Artificial Intelligence · Computer Science 2026-04-14 Mengxuan Wang , Yuxin Chen , Gang Xu , Tao He , Hongjie Jiang , Ming Li

The recent advancements in Large Language Models(LLMs) have had a significant impact on a wide range of fields, from general domains to specialized areas. However, these advancements have also significantly increased the potential for…

Cryptography and Security · Computer Science 2025-10-01 Taegyeong Lee , Jeonghwa Yoo , Hyoungseo Cho , Soo Yong Kim , Yunho Maeng

Despite inheriting security measures from underlying language models, Vision-Language Models (VLMs) may still be vulnerable to safety alignment issues. Through empirical analysis, we uncover two critical findings: scenario-matched images…

Computer Vision and Pattern Recognition · Computer Science 2024-12-02 Shuyang Hao , Bryan Hooi , Jun Liu , Kai-Wei Chang , Zi Huang , Yujun Cai

How well do text-only large language models (LLMs) align with the visual world? We present a systematic evaluation of this question by incorporating frozen representations of various language models into a discriminative vision-language…

Computation and Language · Computer Science 2026-01-19 Jona Ruthardt , Gertjan J. Burghouts , Serge Belongie , Yuki M. Asano

Large Language Models (LLMs) deployed in production environments face a fundamental safety-utility trade-off either a strict filtering mechanisms prevent harmful outputs but often block benign queries or a relaxed controls risk unsafe…

Artificial Intelligence · Computer Science 2026-02-18 Ankit Sharma , Nachiket Tapas , Jyotiprakash Patra

The security concerns surrounding Large Language Models (LLMs) have been extensively explored, yet the safety of Multimodal Large Language Models (MLLMs) remains understudied. In this paper, we observe that Multimodal Large Language Models…

Computer Vision and Pattern Recognition · Computer Science 2024-06-21 Xin Liu , Yichen Zhu , Jindong Gu , Yunshi Lan , Chao Yang , Yu Qiao

Small Language Models (SLMs) are emerging as efficient and economically viable alternatives to Large Language Models (LLMs), offering competitive performance with significantly lower computational costs and latency. These advantages make…

Cryptography and Security · Computer Science 2026-04-01 Md Jueal Mia , Joaquin Molto , Yanzhao Wu , M. Hadi Amini

Ensuring Vision-Language Models (VLMs) generate safe outputs is crucial for their reliable deployment. However, LVLMs suffer from drastic safety degradation compared to their LLM backbone. Even blank or irrelevant images can trigger LVLMs…

Artificial Intelligence · Computer Science 2025-06-02 Wenhan Yang , Spencer Stice , Ali Payani , Baharan Mirzasoleiman

The rapid advancement of vision-language models (VLMs) has brought a lot of attention to their safety alignment. However, existing methods have primarily focused on model undersafety, where the model responds to hazardous queries, while…

Information Retrieval · Computer Science 2025-05-28 Jiahui Geng , Qing Li , Zongxiong Chen , Yuxia Wang , Derui Zhu , Zhuohan Xie , Chenyang Lyu , Xiuying Chen , Preslav Nakov , Fakhri Karray

As Large Language Models (LLMs) become more integrated into our daily lives, it is crucial to identify and mitigate their risks, especially when the risks can have profound impacts on human users and societies. Guardrails, which filter the…

Computation and Language · Computer Science 2024-05-30 Yi Dong , Ronghui Mu , Gaojie Jin , Yi Qi , Jinwei Hu , Xingyu Zhao , Jie Meng , Wenjie Ruan , Xiaowei Huang

This paper presents a comprehensive empirical study on the safety alignment capabilities. We evaluate what matters for safety alignment in LLMs and LRMs to provide essential insights for developing more secure and reliable AI systems. We…

Computation and Language · Computer Science 2026-02-25 Xing Li , Hui-Ling Zhen , Lihao Yin , Xianzhi Yu , Zhenhua Dong , Mingxuan Yuan