English
Related papers

Related papers: HTS-Attack: Heuristic Token Search for Jailbreakin…

200 papers

High-quality and open datasets remain a major bottleneck for text-to-image (T2I) fine-tuning. Despite rapid progress in model architectures and training pipelines, most publicly available fine-tuning datasets suffer from low resolution,…

Computer Vision and Pattern Recognition · Computer Science 2026-02-11 Xu Ma , Yitian Zhang , Qihua Dong , Yun Fu

As Large Language Models (LLMs) are widely used, understanding them systematically is key to improving their safety and realizing their full potential. Although many models are aligned using techniques such as reinforcement learning from…

Machine Learning · Computer Science 2025-05-16 Sajib Biswas , Mao Nishino , Samuel Jacob Chacko , Xiuwen Liu

Large language models (LLMs) have achieved remarkable success across diverse applications but remain vulnerable to jailbreak attacks, where attackers craft prompts that bypass safety alignment and elicit unsafe responses. Among existing…

Computation and Language · Computer Science 2026-03-04 Zhi Xu , Jiaqi Li , Xiaotong Zhang , Hong Yu , Han Liu

Text-to-Image generation models have revolutionized the artwork design process and enabled anyone to create high-quality images by entering text descriptions called prompts. Creating a high-quality prompt that consists of a subject and…

Cryptography and Security · Computer Science 2024-04-16 Xinyue Shen , Yiting Qu , Michael Backes , Yang Zhang

Text-to-image (T2I) models have garnered significant attention for generating high-quality images aligned with text prompts. However, rapid T2I model advancements reveal limitations in early benchmarks, lacking comprehensive evaluations,…

Computer Vision and Pattern Recognition · Computer Science 2025-06-27 Jingjing Chang , Yixiao Fang , Peng Xing , Shuhan Wu , Wei Cheng , Rui Wang , Xianfang Zeng , Gang Yu , Hai-Bao Chen

As large language models (LLMs) are increasingly deployed in critical applications, ensuring their robustness and safety alignment remains a major challenge. Despite the overall success of alignment techniques such as reinforcement learning…

Machine Learning · Computer Science 2025-08-21 Sajib Biswas , Mao Nishino , Samuel Jacob Chacko , Xiuwen Liu

Current text-to-image (T2I) benchmarks evaluate models on rigid prompts, potentially underestimating true generative capabilities due to prompt sensitivity and creating biases that favor certain models while disadvantaging others. We…

Computer Vision and Pattern Recognition · Computer Science 2025-07-08 Haosheng Gan , Berk Tinaz , Mohammad Shahab Sepehri , Zalan Fabian , Mahdi Soltanolkotabi

Recent text-to-image (T2I) models have benefited from large-scale and high-quality data, demonstrating impressive performance. However, these T2I models still struggle to produce images that are aesthetically pleasing, geometrically…

Computer Vision and Pattern Recognition · Computer Science 2024-03-28 Jianshu Guo , Wenhao Chai , Jie Deng , Hsiang-Wei Huang , Tian Ye , Yichen Xu , Jiawei Zhang , Jenq-Neng Hwang , Gaoang Wang

We introduce a novel framework for consolidating multi-turn adversarial ``jailbreak'' prompts into single-turn queries, significantly reducing the manual overhead required for adversarial testing of large language models (LLMs). While…

Computation and Language · Computer Science 2025-08-06 Junwoo Ha , Hyunjun Kim , Sangyoon Yu , Haon Park , Ashkan Yousefpour , Yuna Park , Suhyun Kim

Vision Language Models (VLMs) have demonstrated impressive inference capabilities, but remain vulnerable to jailbreak attacks that can induce harmful or unethical responses. Existing defence methods are predominantly white-box approaches…

Computer Vision and Pattern Recognition · Computer Science 2025-03-25 Xiangyu Yin , Yi Qi , Jinwei Hu , Zhen Chen , Yi Dong , Xingyu Zhao , Xiaowei Huang , Wenjie Ruan

Existing black-box jailbreak attacks achieve certain success on non-reasoning models but degrade significantly on recent SOTA reasoning models. To improve attack ability, inspired by adversarial aggregation strategies, we integrate multiple…

Computation and Language · Computer Science 2026-01-08 Chiyu Zhang , Lu Zhou , Xiaogang Xu , Jiafei Wu , Liming Fang , Zhe Liu

Text-to-image (T2I) diffusion models have drawn attention for their ability to generate high-quality images with precise text alignment. However, these models can also be misused to produce inappropriate content. Existing safety measures,…

Computer Vision and Pattern Recognition · Computer Science 2025-10-07 Hongxiang Zhang , Yifeng He , Hao Chen

Natural language processing models are vulnerable to adversarial examples. Previous textual adversarial attacks adopt gradients or confidence scores to calculate word importance ranking and generate adversarial examples. However, this…

Computation and Language · Computer Science 2024-01-11 Hai Zhu , Zhaoqing Yang , Weiwei Shang , Yuren Wu

Novel research aimed at text-to-image (T2I) generative AI safety often relies on publicly available datasets for training and evaluation, making the quality and composition of these datasets crucial. This paper presents a comprehensive…

Computation and Language · Computer Science 2025-03-04 Rakeen Rouf , Trupti Bavalatti , Osama Ahmed , Dhaval Potdar , Faraz Jawed

Despite the record-breaking performance in Text-to-Image (T2I) generation by Stable Diffusion, less research attention is paid to its adversarial robustness. In this work, we study the problem of adversarial attack generation for Stable…

Computer Vision and Pattern Recognition · Computer Science 2023-04-04 Haomin Zhuang , Yihua Zhang , Sijia Liu

Recent advancements in text-to-image (T2I) diffusion models have demonstrated remarkable capabilities in generating high-fidelity images. However, these models often struggle to faithfully render complex user prompts, particularly in…

Computer Vision and Pattern Recognition · Computer Science 2025-09-24 Linqing Wang , Ximing Xing , Yiji Cheng , Zhiyuan Zhao , Donghao Li , Tiankai Hang , Jiale Tao , Qixun Wang , Ruihuang Li , Comi Chen , Xin Li , Mingrui Wu , Xinchi Deng , Shuyang Gu , Chunyu Wang , Qinglin Lu

Recent progress in text-to-image (T2I) generation underscores the importance of reliable benchmarks in evaluating how accurately generated images reflect the semantics of their textual prompt. However, (1) existing benchmarks lack the…

Computer Vision and Pattern Recognition · Computer Science 2026-02-25 Yibin Wang , Zhimin Li , Yuhang Zang , Jiazi Bu , Yujie Zhou , Yi Xin , Junjun He , Chunyu Wang , Qinglin Lu , Cheng Jin , Jiaqi Wang

Black-box hard-label adversarial attack on text is a practical and challenging task, as the text data space is inherently discrete and non-differentiable, and only the predicted label is accessible. Research on this problem is still in the…

Computation and Language · Computer Science 2024-02-06 Han Liu , Zhi Xu , Xiaotong Zhang , Feng Zhang , Fenglong Ma , Hongyang Chen , Hong Yu , Xianchao Zhang

Text-to-Image In-Context Learning (T2I-ICL) enables customized image synthesis via interleaved text-image examples but faces two mutually reinforcing bottlenecks, compliance failure and prior-dominated hallucination, that form a vicious…

Computer Vision and Pattern Recognition · Computer Science 2026-01-13 Zhiyong Ma , Zhenpeng Li , Yuanjie Shi , Zhengping Li , Jiahao Chen , Qingyuan Chuai

Current large language models (LLMs) provide a strong foundation for large-scale user-oriented natural language tasks. A large number of users can easily inject adversarial text or instructions through the user interface, thus causing LLMs…

Cryptography and Security · Computer Science 2024-11-12 Chong Zhang , Mingyu Jin , Qinkai Yu , Chengzhi Liu , Haochen Xue , Xiaobo Jin