English
Related papers

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

200 papers

Prompt design plays a crucial role in text-to-video (T2V) generation, yet user-provided prompts are often short, unstructured, and misaligned with training data, limiting the generative potential of diffusion-based T2V models. We present…

Computer Vision and Pattern Recognition · Computer Science 2026-05-15 Bingjie Gao , Qianli Ma , Xiaoxue Wu , Shuai Yang , Guanzhou Lan , Haonan Zhao , Jiaxuan Chen , Qingyang Liu , Yu Qiao , Xinyuan Chen , Yaohui Wang , Li Niu

Text-to-video (T2V) generative models have rapidly advanced and found widespread applications across fields like entertainment, education, and marketing. However, the adversarial vulnerabilities of these models remain rarely explored. We…

Computer Vision and Pattern Recognition · Computer Science 2025-07-29 Ruotong Wang , Mingli Zhu , Jiarong Ou , Rui Chen , Xin Tao , Pengfei Wan , Baoyuan Wu

Text-to-Image(T2I) models have achieved remarkable success in image generation and editing, yet these models still have many potential issues, particularly in generating inappropriate or Not-Safe-For-Work(NSFW) content. Strengthening…

Computer Vision and Pattern Recognition · Computer Science 2024-12-17 Sensen Gao , Xiaojun Jia , Yihao Huang , Ranjie Duan , Jindong Gu , Yang Bai , Yang Liu , Qing Guo

Image-to-Video (I2V) generation models, which condition video generation on reference images, have shown emerging visual instruction-following capability, allowing certain visual cues in reference images to act as implicit control signals…

Computer Vision and Pattern Recognition · Computer Science 2026-03-03 Bowen Zheng , Yongli Xiang , Ziming Hong , Zerong Lin , Chaojian Yu , Tongliang Liu , Xinge You

As LLMs continue to shape real-world applications, automated jailbreak generation becomes essential to reveal safety weaknesses and guide model improvement. Existing automatic jailbreak generation methods have not yet fully considered two…

Neural and Evolutionary Computing · Computer Science 2026-05-06 Rui Tang , Kaiyu Xu , Pengsen Cheng , Hao Ren , Haizhou Wang , Shuyu Jiang

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

The evolution of Text-to-video (T2V) generative models, trained on large-scale datasets, has been marked by significant progress. However, the sensitivity of T2V generative models to input prompts highlights the critical role of prompt…

Computer Vision and Pattern Recognition · Computer Science 2025-05-07 Bingjie Gao , Xinyu Gao , Xiaoxue Wu , Yujie Zhou , Yu Qiao , Li Niu , Xinyuan Chen , Yaohui Wang

Image-to-Video (I2V) generation synthesizes dynamic visual content from image and text inputs, providing significant creative control. However, the security of such multimodal systems, particularly their vulnerability to jailbreak attacks,…

Computer Vision and Pattern Recognition · Computer Science 2025-12-09 Songping Wang , Rufan Qian , Yueming Lyu , Qinglong Liu , Linzhuang Zou , Jie Qin , Songhua Liu , Caifeng Shan

Iterative jailbreak methods that repeatedly rewrite and input prompts into large language models (LLMs) to induce harmful outputs -- using the model's previous responses to guide each new iteration -- have been found to be a highly…

Computation and Language · Computer Science 2025-10-21 Masahiro Kaneko , Zeerak Talat , Timothy Baldwin

Despite significant advancements in alignment and content moderation, large language models (LLMs) and text-to-image (T2I) systems remain vulnerable to prompt-based attacks known as jailbreaks. Unlike traditional adversarial examples…

Computer Vision and Pattern Recognition · Computer Science 2025-07-30 Ahmed B Mustafa , Zihan Ye , Yang Lu , Michael P Pound , Shreyank N Gowda

Text-to-image (T2I) models have raised increasing safety concerns due to their capacity to generate NSFW and other banned objects. To mitigate these risks, safety filters and concept removal techniques have been introduced to block…

Cryptography and Security · Computer Science 2026-01-13 Xi Ye , Yiwen Liu , Lina Wang , Run Wang , Geying Yang , Yufei Hou , Jiayi Yu

Using risky text prompts, such as pornography and violent prompts, to test the safety of text-to-image (T2I) models is a critical task. However, existing risky prompt datasets are limited in three key areas: 1) limited risky categories, 2)…

Cryptography and Security · Computer Science 2025-11-24 Chenyu Zhang , Tairen Zhang , Lanjun Wang , Ruidong Chen , Wenhui Li , Anan Liu

Text-to-image (T2I) models such as Stable Diffusion and DALLE remain susceptible to generating harmful or Not-Safe-For-Work (NSFW) content under jailbreak attacks despite deployed safety filters. Existing jailbreak attacks either rely on…

Computer Vision and Pattern Recognition · Computer Science 2026-03-27 Haolun Zheng , Yu He , Tailun Chen , Shuo Shao , Zhixuan Chu , Hongbin Zhou , Lan Tao , Zhan Qin , Kui Ren

Optimization-based jailbreaks typically adopt the Toxic-Continuation setting in large vision-language models (LVLMs), following the standard next-token prediction objective. In this setting, an adversarial image is optimized to make the…

Computer Vision and Pattern Recognition · Computer Science 2025-05-29 Hee-Seon Kim , Minbeom Kim , Wonjun Lee , Kihyun Kim , Changick Kim

Modern text-to-image (T2I) generation systems (e.g., DALL$\cdot$E 3) exploit the memory mechanism, which captures key information in multi-turn interactions for faithful generation. Despite its practicality, the security analyses of this…

Computer Vision and Pattern Recognition · Computer Science 2026-03-05 Shiqian Zhao , Jiayang Liu , Yiming Li , Runyi Hu , Xiaojun Jia , Wenshu Fan , Xiao Bao , Xinfeng Li , Jie Zhang , Wei Dong , Tianwei Zhang , Luu Anh Tuan

Text-to-Image models may generate harmful content, such as pornographic images, particularly when unsafe prompts are submitted. To address this issue, safety filters are often added on top of text-to-image models, or the models themselves…

Cryptography and Security · Computer Science 2026-01-09 Zhengyuan Jiang , Yuepeng Hu , Yuchen Yang , Yinzhi Cao , Neil Zhenqiang Gong

Recent AI systems have shown extremely powerful performance, even surpassing human performance, on various tasks such as information retrieval, language generation, and image generation based on large language models (LLMs). At the same…

Artificial Intelligence · Computer Science 2024-05-29 Minseon Kim , Hyomin Lee , Boqing Gong , Huishuai Zhang , Sung Ju Hwang

Text-to-Image (T2I) models have gained widespread adoption across various applications. Despite the success, the potential misuse of T2I models poses significant risks of generating Not-Safe-For-Work (NSFW) content. To investigate the…

Cryptography and Security · Computer Science 2025-08-07 Xinqi Lyu , Yihao Liu , Yanjie Li , Bin Xiao

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

The increasing sophistication of large vision-language models (LVLMs) has been accompanied by advances in safety alignment mechanisms designed to prevent harmful content generation. However, these defenses remain vulnerable to sophisticated…

Cryptography and Security · Computer Science 2026-04-09 Quanchen Zou , Zonghao Ying , Moyang Chen , Wenzhuo Xu , Yisong Xiao , Yakai Li , Deyue Zhang , Dongdong Yang , Zhao Liu , Xiangzheng Zhang