English
Related papers

Related papers: Token-Level Constraint Boundary Search for Jailbre…

200 papers

The rapid evolution of text-to-image (T2I) models has enabled high-fidelity visual synthesis on a global scale. However, these advancements have introduced significant security risks, particularly regarding the generation of harmful…

Cryptography and Security · Computer Science 2026-01-16 Wonwoo Choi , Minjae Seo , Minkyoo Song , Hwanjo Heo , Seungwon Shin , Myoungsung You

Text-to-Image (T2I) models have shown great performance in generating images based on textual prompts. However, these models are vulnerable to unsafe input to generate unsafe content like sexual, harassment and illegal-activity images.…

Computer Vision and Pattern Recognition · Computer Science 2024-12-13 Zongyu Wu , Hongcheng Gao , Yueze Wang , Xiang Zhang , Suhang Wang

Although recent personalization methods have democratized high-resolution image synthesis by enabling swift concept acquisition with minimal examples and lightweight computation, they also present an exploitable avenue for high accessible…

Computer Vision and Pattern Recognition · Computer Science 2023-12-21 Yihao Huang , Felix Juefei-Xu , Qing Guo , Jie Zhang , Yutong Wu , Ming Hu , Tianlin Li , Geguang Pu , Yang Liu

The generative AI revolution in recent years has been spurred by an expansion in compute power and data quantity, which together enable extensive pre-training of powerful text-to-image (T2I) models. With their greater capabilities to…

Large Language Models (LLMs) are increasingly being integrated into services such as ChatGPT to provide responses to user queries. To mitigate potential harm and prevent misuse, there have been concerted efforts to align the LLMs with human…

Cryptography and Security · Computer Science 2024-12-30 Xiaomeng Hu , Pin-Yu Chen , Tsung-Yi Ho

We introduce Best-of-N (BoN) Jailbreaking, a simple black-box algorithm that jailbreaks frontier AI systems across modalities. BoN Jailbreaking works by repeatedly sampling variations of a prompt with a combination of augmentations - such…

Computation and Language · Computer Science 2024-12-23 John Hughes , Sara Price , Aengus Lynch , Rylan Schaeffer , Fazl Barez , Sanmi Koyejo , Henry Sleight , Erik Jones , Ethan Perez , Mrinank Sharma

Many machine learning algorithms are vulnerable to almost imperceptible perturbations of their inputs. So far it was unclear how much risk adversarial perturbations carry for the safety of real-world machine learning applications because…

Machine Learning · Statistics 2018-02-19 Wieland Brendel , Jonas Rauber , Matthias Bethge

Text-to-image (T2I) models commonly incorporate defense mechanisms to prevent the generation of sensitive images. Unfortunately, recent jailbreak attacks have shown that adversarial prompts can effectively bypass these mechanisms and induce…

Cryptography and Security · Computer Science 2026-03-25 Chenyu Zhang , Lanjun Wang , Yiwen Ma , Wenhui Li , Yi Tu , An-An Liu

Recent text-to-video (T2V) models can synthesize complex videos from lightweight natural language prompts, raising urgent concerns about safety alignment in the event of misuse in the real world. Prior jailbreak attacks typically rewrite…

Cryptography and Security · Computer Science 2026-03-10 Moyang Chen , Zonghao Ying , Wenzhuo Xu , Quancheng Zou , Deyue Zhang , Dongdong Yang , Xiangzheng Zhang

Recently, Text-to-Image (T2I) synthesis technology has made tremendous strides. Numerous representative T2I models have emerged and achieved promising application outcomes, such as DALL-E, Stable Diffusion, Imagen, etc. In practice, it has…

Cryptography and Security · Computer Science 2025-09-24 Wenbo Jiang , Jiaming He , Hongwei Li , Rui Zhang , Hanxiao Chen , Meng Hao , Haomiao Yang , Qingchuan Zhao , Guowen Xu

Adversarial robustness in structured data remains an underexplored frontier compared to vision and language domains. In this work, we introduce a novel black-box, decision-based adversarial attack tailored for tabular data. Our approach…

Machine Learning · Computer Science 2025-11-25 Roie Kazoom , Yuval Ratzabi , Etamar Rothstein , Ofer Hadar

Text-to-image (T2I) models, though exhibiting remarkable creativity in image generation, can be exploited to produce unsafe images. Existing safety measures, e.g., content moderation or model alignment, fail in the presence of white-box…

Cryptography and Security · Computer Science 2025-10-21 Xinfeng Li , Shengyuan Pang , Jialin Wu , Jiangyi Deng , Huanlong Zhong , Yanjiao Chen , Jie Zhang , Wenyuan Xu

Text-to-image (T2I) models have significantly advanced in producing high-quality images. However, such models have the ability to generate images containing not-safe-for-work (NSFW) content, such as pornography, violence, political content,…

Cryptography and Security · Computer Science 2025-05-15 Longtian Wang , Xiaofei Xie , Tianlin Li , Yuhan Zhi , Chao Shen

Despite the impressive synthesis quality of text-to-image (T2I) diffusion models, their black-box deployment poses significant regulatory challenges: Malicious actors can fine-tune these models to generate illegal content, circumventing…

Computer Vision and Pattern Recognition · Computer Science 2025-03-31 Zhuomeng Zhang , Fangqi Li , Chong Di , Hongyu Zhu , Hanyi Wang , Shilin Wang

Recent text-to-image (T2I) diffusion models show outstanding performance in generating high-quality images conditioned on textual prompts. However, they fail to semantically align the generated images with the prompts due to their limited…

Computer Vision and Pattern Recognition · Computer Science 2023-12-15 Ruichen Wang , Zekang Chen , Chen Chen , Jian Ma , Haonan Lu , Xiaodong Lin

Text-to-image (T2I) generation aims to synthesize images from textual prompts, which jointly specify what must be shown and imply what can be inferred, which thus correspond to two core capabilities: \textbf{\textit{composition}} and…

Computer Vision and Pattern Recognition · Computer Science 2026-03-03 Ouxiang Li , Yuan Wang , Xinting Hu , Huijuan Huang , Rui Chen , Jiarong Ou , Xin Tao , Pengfei Wan , Xiaojuan Qi , Fuli Feng

Recent research indicates that large language models (LLMs) are susceptible to jailbreaking attacks that can generate harmful content. This paper introduces a novel token-level attack method, Adaptive Dense-to-Sparse Constrained…

Machine Learning · Computer Science 2025-02-13 Kai Hu , Weichen Yu , Yining Li , Kai Chen , Tianjun Yao , Xiang Li , Wenhe Liu , Lijun Yu , Zhiqiang Shen , Matt Fredrikson

Jailbreaking techniques trick Large Language Models (LLMs) into producing restricted output, posing a potential threat. One line of defense is to use another LLM as a Judge to evaluate the harmfulness of generated text. However, we reveal…

Computation and Language · Computer Science 2025-08-19 Zhipeng Wei , Yuqi Liu , N. Benjamin Erichson

Fine-tuning large language models (LLMs) on custom datasets has become a standard approach for adapting these models to specific domains and applications. However, recent studies have shown that such fine-tuning can lead to significant…

Computation and Language · Computer Science 2026-03-03 Yanping Li , Zhening Liu , Zijian Li , Zehong Lin , Jun Zhang

Text-to-image (T2I) generation has made remarkable progress in producing high-quality images, but a fundamental challenge remains: creating backgrounds that naturally accommodate text placement without compromising image quality. This…

Computer Vision and Pattern Recognition · Computer Science 2025-05-14 Tianyi Liang , Jiangqi Liu , Yifei Huang , Shiqi Jiang , Jianshen Shi , Changbo Wang , Chenhui Li