English
Related papers

Related papers: SEA: Low-Resource Safety Alignment for Multimodal …

200 papers

Entity alignment (EA) aims to find equivalent entities in different knowledge graphs (KGs). State-of-the-art EA approaches generally use Graph Neural Networks (GNNs) to encode entities. However, most of them train the models and evaluate…

Computation and Language · Computer Science 2023-04-17 Junyang Wu , Tianyi Li , Lu Chen , Yunjun Gao , Ziheng Wei

Large Language Models (LLMs) and Vision Language Models (VLMs) have demonstrated impressive capabilities but remain vulnerable to jailbreaking attacks, where adversaries exploit textual or visual triggers to bypass safety guardrails. Recent…

Cryptography and Security · Computer Science 2026-05-15 Yi Wang , Hongye Qiu , Yue Xu , Sibei Yang , Zhan Qin , Minlie Huang , Wenjie Wang

Recent breakthroughs in Large Language Models (LLMs) have led to their adoption across a wide range of tasks, ranging from code generation to machine translation and sentiment analysis, etc. Red teaming/Safety alignment efforts show that…

Computation and Language · Computer Science 2024-09-25 Essa Jan , Nouar AlDahoul , Moiz Ali , Faizan Ahmad , Fareed Zaffar , Yasir Zaki

Large Language Models (LLMs) generating unsafe responses to toxic prompts is a significant issue in their applications. While various efforts aim to address this safety concern, previous approaches often demand substantial human data…

Computation and Language · Computer Science 2024-12-12 Yuxiao Lu , Arunesh Sinha , Pradeep Varakantham

Multimodal large language models (MLLMs) are rapidly evolving, presenting increasingly complex safety challenges. However, current dataset construction methods, which are risk-oriented, fail to cover the growing complexity of real-world…

Computer Vision and Pattern Recognition · Computer Science 2026-02-27 Jingen Qu , Lijun Li , Bo Zhang , Yichen Yan , Jing Shao

Multimodal Large Language Models (MLLMs) extend text-only LLMs with visual reasoning, but also introduce new safety failure modes under visually grounded instructions. We study comic-template jailbreaks that embed harmful goals inside…

Cryptography and Security · Computer Science 2026-04-24 Rui Yang Tan , Yujia Hu , Roy Ka-Wei Lee

Although instruction-tuned large language models (LLMs) have exhibited remarkable capabilities across various NLP tasks, their effectiveness on other data modalities beyond text has not been fully studied. In this work, we propose…

Computation and Language · Computer Science 2023-06-16 Chenyang Lyu , Minghao Wu , Longyue Wang , Xinting Huang , Bingshuai Liu , Zefeng Du , Shuming Shi , Zhaopeng Tu

Large language models (LLMs) have been used in many application domains, including cyber security. The application of LLMs in the cyber security domain presents significant opportunities, such as for enhancing threat analysis and malware…

Cryptography and Security · Computer Science 2025-09-18 Adel ElZemity , Budi Arief , Shujun Li

Fine-tuning large language models (LLMs) with low-rank adaptation (LoRA) is a cost-effective way to incorporate information from a specific dataset. However, when a problem requires incorporating information from multiple datasets - as in…

Machine Learning · Computer Science 2026-04-03 Liyi Zhang , Jake Snell , Thomas L. Griffiths

Large Audio Language Models (LALMs) have extended the capabilities of Large Language Models (LLMs) by enabling audio-based human interactions. However, recent research has revealed that LALMs remain vulnerable to harmful queries due to…

Computation and Language · Computer Science 2025-05-27 Hao Yang , Lizhen Qu , Ehsan Shareghi , Gholamreza Haffari

The goal of multimodal alignment is to learn a single latent space that is shared between multimodal inputs. The most powerful models in this space have been trained using massive datasets of paired inputs and large-scale computational…

Recently, multimodal large language models (MLLMs) have emerged as a unified paradigm for language and image generation. Compared with diffusion models, MLLMs possess a much stronger capability for semantic understanding, enabling them to…

Computer Vision and Pattern Recognition · Computer Science 2026-03-26 Ye Leng , Junjie Chu , Mingjie Li , Chenhao Lin , Chao Shen , Michael Backes , Yun Shen , Yang Zhang

With the recent unprecedented advancements in Artificial Intelligence (AI) computing, progress in Large Language Models (LLMs) is accelerating rapidly, presenting challenges in establishing clear guidelines, particularly in the field of…

Cryptography and Security · Computer Science 2024-09-04 Nafis Tanveer Islam , Joseph Khoury , Andrew Seong , Elias Bou-Harb , Peyman Najafirad

Large Language Models (LLMs) can generate code but often introduce security vulnerabilities, logical inconsistencies, and compilation errors. Prior work demonstrates that LLMs benefit substantially from structured feedback, static analysis,…

Cryptography and Security · Computer Science 2026-01-05 Vidyut Sriram , Sawan Pandita , Achintya Lakshmanan , Aneesh Shamraj , Suman Saha

The creation of high-quality human-labeled image-caption datasets presents a significant bottleneck in the development of Visual-Language Models (VLMs). In this work, we investigate an approach that leverages the strengths of Large Language…

Computer Vision and Pattern Recognition · Computer Science 2024-06-10 Sahand Sharifzadeh , Christos Kaplanis , Shreya Pathak , Dharshan Kumaran , Anastasija Ilic , Jovana Mitrovic , Charles Blundell , Andrea Banino

Multimodal Large Language Models (MLLMs) are showing strong safety concerns (e.g., generating harmful outputs for users), which motivates the development of safety evaluation benchmarks. However, we observe that existing safety benchmarks…

Cryptography and Security · Computer Science 2024-10-25 Zonghao Ying , Aishan Liu , Siyuan Liang , Lei Huang , Jinyang Guo , Wenbo Zhou , Xianglong Liu , Dacheng Tao

A robust Multimodal Large Language Model (MLLM) for Earth Observation should maintain consistent interpretation and reasoning under realistic input variations. However, current Remote Sensing MLLMs fail to meet this requirement. Trained on…

Computer Vision and Pattern Recognition · Computer Science 2026-04-21 Rui Min , Liang Yao , Shiyu Miao , Shengxiang Xu , Yuxuan Liu , Chuanyi Zhang , Shimin Di , Fan Liu

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 increasing availability of traffic videos functioning on a 24/7/365 time scale has the great potential of increasing the spatio-temporal coverage of traffic accidents, which will help improve traffic safety. However, analyzing footage…

Computer Vision and Pattern Recognition · Computer Science 2025-06-18 Ruixuan Zhang , Beichen Wang , Juexiao Zhang , Zilin Bian , Chen Feng , Kaan Ozbay

Multimodal Large Language Models (MLLMs) have achieved impressive performance and have been put into practical use in commercial applications, but they still have potential safety mechanism vulnerabilities. Jailbreak attacks are red teaming…

Cryptography and Security · Computer Science 2025-06-30 Shiji Zhao , Ranjie Duan , Fengxiang Wang , Chi Chen , Caixin Kang , Shouwei Ruan , Jialing Tao , YueFeng Chen , Hui Xue , Xingxing Wei