English
Related papers

Related papers: T2V-OptJail: Discrete Prompt Optimization for Text…

200 papers

Text-to-Image (T2I) models have raised security concerns due to their potential to generate inappropriate or harmful images. In this paper, we propose UPAM, a novel framework that investigates the robustness of T2I models from the attack…

Computer Vision and Pattern Recognition · Computer Science 2024-05-28 Duo Peng , Qiuhong Ke , Jun Liu

State-of-the-art text-to-video (T2V) generators frequently violate physical laws despite high visual quality. We show this stems from insufficient physical constraints in prompts rather than model limitations: manually adding physics…

Computer Vision and Pattern Recognition · Computer Science 2026-03-05 Shang Wu , Chenwei Xu , Zhuofan Xia , Weijian Li , Lie Lu , Pranav Maneriker , Fan Du , Manling Li , Han Liu

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

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

Jailbreaks are adversarial attacks designed to bypass the built-in safety mechanisms of large language models. Automated jailbreaks typically optimize an adversarial suffix or adapt long prompt templates by forcing the model to generate the…

Computation and Language · Computer Science 2025-10-31 Raffaele Mura , Giorgio Piras , Kamilė Lukošiūtė , Maura Pintor , Amin Karbasi , Battista Biggio

Adversarial prompts generated using gradient-based methods exhibit outstanding performance in performing automatic jailbreak attacks against safety-aligned LLMs. Nevertheless, due to the discrete nature of texts, the input gradient of LLMs…

Cryptography and Security · Computer Science 2024-11-04 Qizhang Li , Yiwen Guo , Wangmeng Zuo , Hao Chen

Impressive advances in text-to-image (T2I) generative models have yielded a plethora of high performing models which are able to generate aesthetically appealing, photorealistic images. Despite the progress, these models still struggle to…

Computer Vision and Pattern Recognition · Computer Science 2024-03-27 Oscar Mañas , Pietro Astolfi , Melissa Hall , Candace Ross , Jack Urbanek , Adina Williams , Aishwarya Agrawal , Adriana Romero-Soriano , Michal Drozdzal

Recent text-to-image (T2I) models have had great success, and many benchmarks have been proposed to evaluate their performance and safety. However, they only consider explicit prompts while neglecting implicit prompts (hint at a target…

Computers and Society · Computer Science 2024-05-29 Yue Yang , Yuqi Lin , Hong Liu , Wenqi Shao , Runjian Chen , Hailong Shang , Yu Wang , Yu Qiao , Kaipeng Zhang , Ping Luo

Large Language Models face security threats from jailbreak attacks. Existing research has predominantly focused on prompt-level attacks while largely ignoring the underexplored attack surface of user-controlled response prefilling. This…

Cryptography and Security · Computer Science 2025-08-27 Yakai Li , Jiekang Hu , Weiduan Sang , Luping Ma , Dongsheng Nie , Weijuan Zhang , Aimin Yu , Yi Su , Qingjia Huang , Qihang Zhou

Jailbreak attacks -- adversarial prompts that bypass LLM alignment through purely linguistic manipulation -- pose a growing operational security threat, yet the field lacks large-scale, reproducible infrastructure for generating,…

Cryptography and Security · Computer Science 2026-05-12 Ismail Hossain , Tanzim Ahad , Md Jahangir Alam , Sai Puppala , Syed Bahauddin Alam , Sajedul Talukder

Intent detection, a core component of natural language understanding, has considerably evolved as a crucial mechanism in safeguarding large language models (LLMs). While prior work has applied intent detection to enhance LLMs' moderation…

Computation and Language · Computer Science 2025-08-26 Jun Zhuang , Haibo Jin , Ye Zhang , Zhengjian Kang , Wenbin Zhang , Gaby G. Dagher , Haohan Wang

Jailbreak attacks to Large audio-language models (LALMs) are studied recently, but they exclusively focused on the attack scenario where the adversary can fully manipulate user prompts (named strong adversary) and limited in effectiveness,…

Cryptography and Security · Computer Science 2026-02-04 Guangke Chen , Fu Song , Zhe Zhao , Xiaojun Jia , Yang Liu , Yanchen Qiao , Weizhe Zhang , Weiping Tu , Yuhong Yang , Bo Du

We investigate the generation of minority samples using pretrained text-to-image (T2I) latent diffusion models. Minority instances, in the context of T2I generation, can be defined as ones living on low-density regions of text-conditional…

Computer Vision and Pattern Recognition · Computer Science 2025-04-07 Soobin Um , Jong Chul Ye

Text-to-Image (T2I) generation has advanced rapidly in recent years, but they also raise safety concerns due to the potential production of harmful content. In the practical deployments, T2I services typically adopt full-chain defenses that…

Computer Vision and Pattern Recognition · Computer Science 2026-03-12 Jiangtao Liu , Zhaoxin Wang , Handing Wang , Cong Tian , Yaochu Jin

Tool-calling text-to-image (T2I) agents can plan and execute multi-step tool chains to accomplish complex generation and editing queries. However, this capability introduces a new safety attack surface: harmful outputs may arise from tool…

Multiagent Systems · Computer Science 2026-05-11 Jianming Chen , Yawen Wang , Junjie Wang , Zhe Liu , Qing Wang , Fanjiang Xu

The rapid advancement of text-to-image (T2I) models, such as Stable Diffusion, has enhanced their capability to synthesize images from textual prompts. However, this progress also raises significant risks of misuse, including the generation…

Computer Vision and Pattern Recognition · Computer Science 2025-06-24 Yu Xie , Chengjie Zeng , Lingyun Zhang , Yanwei Fu

Safety alignment mechanism are essential for preventing large language models (LLMs) from generating harmful information or unethical content. However, cleverly crafted prompts can bypass these safety measures without accessing the model's…

Computation and Language · Computer Science 2025-01-31 Sunbowen Lee , Shiwen Ni , Chi Wei , Shuaimin Li , Liyang Fan , Ahmadreza Argha , Hamid Alinejad-Rokny , Ruifeng Xu , Yicheng Gong , Min Yang

While Large Language Models (LLMs) have achieved tremendous success in various applications, they are also susceptible to jailbreaking attacks. Several primary defense strategies have been proposed to protect LLMs from producing harmful…

Machine Learning · Computer Science 2024-11-01 Yichuan Mo , Yuji Wang , Zeming Wei , Yisen Wang

Jailbreak attacks reveal critical vulnerabilities in Large Language Models (LLMs) by causing them to generate harmful or unethical content. Evaluating these threats is particularly challenging due to the evolving nature of LLMs and the…

Machine Learning · Computer Science 2025-07-11 Peiyan Zhang , Haibo Jin , Liying Kang , Haohan Wang

Text-to-Image (T2I) models, represented by DALL$\cdot$E and Midjourney, have gained huge popularity for creating realistic images. The quality of these images relies on the carefully engineered prompts, which have become valuable…

Cryptography and Security · Computer Science 2026-01-22 Shiqian Zhao , Chong Wang , Yiming Li , Yihao Huang , Wenjie Qu , Siew-Kei Lam , Yi Xie , Kangjie Chen , Jie Zhang , Tianwei Zhang