English
Related papers

Related papers: Conditioned Activation Transport for T2I Safety St…

200 papers

Text-to-Image(T2I) models typically deploy safety filters to prevent the generation of sensitive images. Unfortunately, recent jailbreaking attack methods manually design instructions for the LLM to generate adversarial prompts, which…

Cryptography and Security · Computer Science 2025-11-24 Chenyu Zhang , Lanjun Wang , Yiwen Ma , Wenhui Li , An-An Liu

Text-to-image (T2I) models have substantially improved image fidelity and prompt adherence, yet their creativity remains constrained by reliance on discrete natural language prompts. When presented with fuzzy prompts such as ``a creative…

Computer Vision and Pattern Recognition · Computer Science 2026-03-19 Ruixiao Shi , Fu Feng , Yucheng Xie , Xu Yang , Jing Wang , Xin Geng

Diffusion models have recently achieved remarkable advancements in terms of image quality and fidelity to textual prompts. Concurrently, the safety of such generative models has become an area of growing concern. This work introduces a…

Computer Vision and Pattern Recognition · Computer Science 2025-06-12 Tong Liu , Zhixin Lai , Jiawen Wang , Gengyuan Zhang , Shuo Chen , Philip Torr , Vera Demberg , Volker Tresp , Jindong Gu

Most existing image tokenizers encode images into a fixed number of tokens or patches, overlooking the inherent variability in image complexity. To address this, we introduce Content-Adaptive Tokenizer (CAT), which dynamically adjusts…

Computer Vision and Pattern Recognition · Computer Science 2025-01-07 Junhong Shen , Kushal Tirumala , Michihiro Yasunaga , Ishan Misra , Luke Zettlemoyer , Lili Yu , Chunting Zhou

LLMs have shown remarkable capabilities, but precisely controlling their response behavior remains challenging. Existing activation steering methods alter LLM behavior indiscriminately, limiting their practical applicability in settings…

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

Text-to-image (T2I) models have emerged as a significant advancement in generative AI; however, there exist safety concerns regarding their potential to produce harmful image outputs even when users input seemingly safe prompts. This…

Computers and Society · Computer Science 2024-08-19 Susan Hao , Renee Shelby , Yuchi Liu , Hansa Srinivasan , Mukul Bhutani , Burcu Karagol Ayan , Ryan Poplin , Shivani Poddar , Sarah Laszlo

Jailbreak attacks can circumvent model safety guardrails and reveal critical blind spots. Prior attacks on text-to-video (T2V) models typically add adversarial perturbations to obviously unsafe prompts, which are often easy to detect and…

Computer Vision and Pattern Recognition · Computer Science 2026-03-09 Zonghao Ying , Moyang Chen , Nizhang Li , Zhiqiang Wang , Wenxin Zhang , Quanchen Zou , Zonglei Jing , Aishan Liu , Xianglong Liu

Text-to-image (T2I) models are widespread, but their limited safety guardrails expose end users to harmful content and potentially allow for model misuse. Current safety measures are typically limited to text-based filtering or concept…

Computer Vision and Pattern Recognition · Computer Science 2025-07-01 Runtao Liu , I Chieh Chen , Jindong Gu , Jipeng Zhang , Renjie Pi , Qifeng Chen , Philip Torr , Ashkan Khakzar , Fabio Pizzati

In recent years, text-to-image (T2I) diffusion models have gained significant attention for their ability to generate high quality images reflecting text prompts. However, their growing popularity has also led to the emergence of backdoor…

Cryptography and Security · Computer Science 2025-08-05 Shengfang Zhai , Jiajun Li , Yue Liu , Huanran Chen , Zhihua Tian , Wenjie Qu , Qingni Shen , Ruoxi Jia , Yinpeng Dong , Jiaheng Zhang

Text-guided image manipulation with diffusion models enables flexible and precise editing based on prompts, but raises ethical and copyright concerns due to potential unauthorized modifications. To address this, we propose SecureT2I, a…

Cryptography and Security · Computer Science 2025-07-08 Xiaodong Wu , Xiangman Li , Qi Li , Jianbing Ni , Rongxing Lu

Text-to-image (T2I) models such as Stable Diffusion have advanced rapidly and are now widely used in content creation. However, these models can be misused to generate harmful content, including nudity or violence, posing significant safety…

Cryptography and Security · Computer Science 2025-06-13 Zilong Wang , Xiang Zheng , Xiaosen Wang , Bo Wang , Xingjun Ma , Yu-Gang Jiang

Recent text-to-image (T2I) models have exhibited remarkable performance in generating high-quality images from text descriptions. However, these models are vulnerable to misuse, particularly generating not-safe-for-work (NSFW) content, such…

Computer Vision and Pattern Recognition · Computer Science 2026-05-12 Lingzhi Yuan , Xinfeng Li , Chejian Xu , Guanhong Tao , Xiaojun Jia , Yihao Huang , Wei Dong , Yang Liu , Bo Li

Alignment in LLMs is more brittle than commonly assumed: misalignment can be triggered by adversarial prompts, benign fine-tuning, emergent misalignment, and goal misgeneralization. Recent evidence suggests that some misalignment behaviors…

Artificial Intelligence · Computer Science 2026-04-10 Niklas Herbster , Martin Zborowski , Alberto Tosato , Gauthier Gidel , Tommaso Tosato

Large-scale pre-trained generative models are taking the world by storm, due to their abilities in generating creative content. Meanwhile, safeguards for these generative models are developed, to protect users' rights and safety, most of…

Cryptography and Security · Computer Science 2024-10-14 Guanlin Li , Kangjie Chen , Shudong Zhang , Jie Zhang , Tianwei Zhang

Existing promptable segmentation methods in the medical imaging field primarily consider either textual or visual prompts to segment relevant objects, yet they often fall short when addressing anomalies in medical images, like tumors, which…

Computer Vision and Pattern Recognition · Computer Science 2024-11-01 Zhongzhen Huang , Yankai Jiang , Rongzhao Zhang , Shaoting Zhang , Xiaofan Zhang

Vehicle-to-Infrastructure (V2I) communications are increasingly supporting highway operations such as electronic toll collection, carpooling, and vehicle platooning. In this paper we study the incentives of strategic misbehavior by…

Computer Science and Game Theory · Computer Science 2018-08-23 Manxi Wu , Li Jin , Saurabh Amin , Patrick Jaillet

Despite the integration of safety alignment and external filters, text-to-image (T2I) generative systems are still susceptible to producing harmful content, such as sexual or violent imagery. This raises serious concerns about unintended…

Cryptography and Security · Computer Science 2025-12-09 Boheng Li , Junjie Wang , Yiming Li , Zhiyang Hu , Leyi Qi , Jianshuo Dong , Run Wang , Han Qiu , Zhan Qin , Tianwei Zhang

When language model agents tackle complex software engineering tasks, they often degrade over long trajectories, which we define as *agent drift*. We focus on two recurring failure modes *overthinking* and *overacting*, i.e., where the…

Artificial Intelligence · Computer Science 2026-05-08 Yuan Sui , Yulin Chen , Yibo Li , Xue Jiang , Yufei He , Yihong Dong , Xiaoxin He , Tianyu Gao , Bryan Hooi

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