English
Related papers

Related papers: ART: Automatic Red-teaming for Text-to-Image Model…

200 papers

Recent advances in Large Language Models (LLMs) have spurred transformative applications in various domains, ranging from open-source to proprietary LLMs. However, jailbreak attacks, which aim to break safety alignment and user compliance…

Artificial Intelligence · Computer Science 2025-12-09 Chen Xiong , Pin-Yu Chen , Tsung-Yi Ho

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

Text-to-image models can generate harmful images when presented with unsafe prompts, posing significant safety and societal risks. Alignment methods aim to modify these models to ensure they generate only non-harmful images, even when…

Cryptography and Security · Computer Science 2025-03-03 Yuepeng Hu , Zhengyuan Jiang , Neil Zhenqiang Gong

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 have become prevalent across numerous applications, making their robust evaluation against adversarial attacks a critical priority. Continuous access to new and challenging adversarial prompts across diverse…

Machine Learning · Computer Science 2025-07-25 Jessica Quaye , Charvi Rastogi , Alicia Parrish , Oana Inel , Minsuk Kahng , Lora Aroyo , Vijay Janapa Reddi

The emergence of diffusion models has significantly advanced image synthesis. The recent studies of model interaction and self-corrective reasoning approach in large language models offer new insights for enhancing text-to-image models.…

Computer Vision and Pattern Recognition · Computer Science 2024-12-19 Zhongjie Duan , Qianyi Zhao , Cen Chen , Daoyuan Chen , Wenmeng Zhou , Yaliang Li , Yingda Chen

In the rapidly advancing field of artificial intelligence, the concept of Red-Teaming or Jailbreaking large language models (LLMs) has emerged as a crucial area of study. This approach is especially significant in terms of assessing and…

Computation and Language · Computer Science 2024-05-17 Rima Hazra , Sayan Layek , Somnath Banerjee , Soujanya Poria

Ensuring the safety of autonomous vehicles requires virtual scenario-based testing, which depends on the robust evaluation and generation of safety-critical scenarios. So far, researchers have used scenario-based testing frameworks that…

Artificial Intelligence · Computer Science 2025-07-21 Yuan Gao , Mattia Piccinini , Korbinian Moller , Amr Alanwar , Johannes Betz

Disinformation is among the top risks of generative artificial intelligence (AI) misuse. Global adoption of generative AI necessitates red-teaming evaluations (i.e., systematic adversarial probing) that are robust across diverse languages…

Computation and Language · Computer Science 2025-09-24 Alejandro Cuevas , Saloni Dash , Bharat Kumar Nayak , Dan Vann , Madeleine I. G. Daepp

Recent work has shown that inference-time reasoning and reflection can improve text-to-image generation without retraining. However, existing approaches often rely on implicit, holistic critiques or unconstrained prompt rewrites, making…

Computer Vision and Pattern Recognition · Computer Science 2026-01-22 V. Kovalev , A. Kuvshinov , A. Buzovkin , D. Pokidov , D. Timonin

Visuomotor policies trained via imitation learning are capable of performing challenging manipulation tasks, but are often extremely brittle to lighting, visual distractors, and object locations. These vulnerabilities can depend…

Large Language Models (LLMs) have demonstrated remarkable capabilities in natural language processing tasks, but their vulnerability to jailbreak attacks poses significant security risks. This survey paper presents a comprehensive analysis…

Computation and Language · Computer Science 2024-12-18 Tarun Raheja , Nilay Pochhi , F. D. C. M. Curie

Text-to-image (T2I) generative models have achieved remarkable visual fidelity, yet remain vulnerable to generating unsafe content. Existing safety defenses typically intervene internally within the generative model, but suffer from severe…

Computer Vision and Pattern Recognition · Computer Science 2026-01-21 Xiangtao Meng , Yingkai Dong , Ning Yu , Li Wang , Zheng Li , Shanqing Guo

Text-to-image models are powerful for producing high-quality images based on given text prompts, but crafting these prompts often requires specialized vocabulary. To address this, existing methods train rewriting models with supervision…

Computer Vision and Pattern Recognition · Computer Science 2025-12-16 Hongji Yang , Yucheng Zhou , Wencheng Han , Jianbing Shen

Safety filters in commercial text-to-image (T2I) models systematically block legitimate artistic content involving the human figure, treating classical nude photography with the same restrictiveness as explicit material. While prior…

Multimedia · Computer Science 2026-03-24 Luca Cazzaniga

Generative language models are increasingly used for contract drafting and enhancement, creating a scenario where competing parties deploy different language models against each other. This introduces not only a game-theory challenge but…

Computation and Language · Computer Science 2025-01-03 Arinbjörn Kolbeinsson , Benedikt Kolbeinsson

Language-conditioned robot models have the potential to enable robots to perform a wide range of tasks based on natural language instructions. However, assessing their safety and effectiveness remains challenging because it is difficult to…

Large generative AI models (GMs) like GPT and DALL-E are trained to generate content for general, wide-ranging purposes. GM content filters are generalized to filter out content which has a risk of harm in many cases, e.g., hate speech.…

Human-Computer Interaction · Computer Science 2023-06-07 Logan Stapleton , Jordan Taylor , Sarah Fox , Tongshuang Wu , Haiyi Zhu

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

Generative AI is increasingly important in software engineering, including safety engineering, where its use ensures that software does not cause harm to people. This also leads to high quality requirements for generative AI. Therefore, the…

Software Engineering · Computer Science 2024-04-25 Florian Geissler , Karsten Roscher , Mario Trapp