English
Related papers

Related papers: The Violation State: Safety State Persistence in a…

200 papers

The internet has become the main source of data to train modern text-to-image or vision-language models, yet it is increasingly unclear whether web-scale data collection practices for training AI systems adequately respect data owners'…

Computers and Society · Computer Science 2026-04-10 Chung Peng Lee , Rachel Hong , Harry H. Jiang , Aster Plotnik , William Agnew , Jamie Morgenstern

Training multimodal generative models on large, uncurated datasets can result in users being exposed to harmful, unsafe and controversial or culturally-inappropriate outputs. While model editing has been proposed to remove or filter…

Computer Vision and Pattern Recognition · Computer Science 2025-03-06 Jordan Vice , Naveed Akhtar , Mubarak Shah , Richard Hartley , Ajmal Mian

The recent success of ChatGPT and GPT-4 has drawn widespread attention to multimodal dialogue systems. However, there is a lack of datasets in the academic community that can effectively evaluate the multimodal generation capabilities of…

Computer Vision and Pattern Recognition · Computer Science 2024-02-20 Zhiwei Zhang , Yuliang Liu

Large language models deployed as agents increasingly interact with external systems through tool calls--actions with real-world consequences that text outputs alone do not carry. Safety evaluations, however, overwhelmingly measure…

Artificial Intelligence · Computer Science 2026-02-20 Arnold Cartagena , Ariane Teixeira

The widespread deployment of high-fidelity generative models has intensified the need for reliable mechanisms for provenance and content authentication. In-processing watermarking, embedding a signature into the generative model's synthesis…

Computer Vision and Pattern Recognition · Computer Science 2026-03-31 Anirudh Nakra , Min Wu

Watermarks for AI-generated images are meant to support downstream decisions about provenance, manipulation, and trust. In the settings that motivate watermark removal, therefore, success means more than causing the watermark test to fail.…

Cryptography and Security · Computer Science 2026-05-12 Yevin Nikhel Goonatilake , Giuseppe Ateniese

High-fidelity text-to-image diffusion models have revolutionized visual content generation, but their widespread use raises significant ethical concerns, including intellectual property protection and the misuse of synthetic media. To…

Computer Vision and Pattern Recognition · Computer Science 2025-08-21 Yunzhuo Chen , Naveed Akhtar , Nur Al Hasan Haldar , Ajmal Mian

As AI advances, copyrighted content faces growing risk of unauthorized use, whether through model training or direct misuse. Building upon invisible adversarial perturbation, recent works developed copyright protections against specific AI…

Machine Learning · Computer Science 2025-06-04 Tianci Liu , Tong Yang , Quan Zhang , Qi Lei

Safety evaluation of multimodal foundation models often treats vision and language inputs separately, missing risks from joint interpretation where benign content becomes harmful in combination. Existing approaches also fail to distinguish…

Computer Vision and Pattern Recognition · Computer Science 2025-12-04 Shruti Palaskar , Leon Gatys , Mona Abdelrahman , Mar Jacobo , Larry Lindsey , Rutika Moharir , Gunnar Lund , Yang Xu , Navid Shiee , Jeffrey Bigham , Charles Maalouf , Joseph Yitan Cheng

Human safety awareness gaps often prevent the timely recognition of everyday risks. In solving this problem, a proactive safety artificial intelligence (AI) system would work better than a reactive one. Instead of just reacting to users'…

Computation and Language · Computer Science 2025-10-21 Youliang Yuan , Wenxiang Jiao , Yuejin Xie , Chihao Shen , Menghan Tian , Wenxuan Wang , Jen-tse Huang , Pinjia He

This work aims to create a multimodal AI system that chats with humans and shares relevant photos. While earlier works were limited to dialogues about specific objects or scenes within images, recent works have incorporated images into…

Computation and Language · Computer Science 2023-05-08 Min Young Lee

As artificial intelligence tools become ubiquitous in education, maintaining academic integrity while accommodating pedagogically beneficial AI assistance presents unprecedented challenges. Current AI detection systems fail to control false…

Applications · Statistics 2025-08-01 Yangxinyu Xie , Xuyang Chen , Zhimei Ren , Weijie J. Su

As Large Multimodal Models (LMMs) become integral to daily digital life, understanding their safety architectures is a critical problem for AI Alignment. This paper presents a systematic analysis of OpenAI's GPT-4o mini, a globally deployed…

Machine Learning · Computer Science 2026-05-26 Niruthiha Selvanayagam , Ted Kurti

Watermarking embeds information into digital content like images, audio, or text, imperceptible to humans but robustly detectable by specific algorithms. This technology has important applications in many challenges of the industry such as…

Cryptography and Security · Computer Science 2025-02-11 Pierre Fernandez

Millions of users turn to consumer AI chatbots to discuss mental health and behavioral concerns. While this presents unprecedented opportunities to deliver population-level support, it also highlights an urgent need for rigorous and…

Neurons and Cognition · Quantitative Biology 2026-03-10 Veith Weilnhammer , Kevin YC Hou , Lennart Luettgau , Christopher Summerfield , Raymond Dolan , Matthew M Nour

Conversational large language models are fine-tuned for both instruction-following and safety, resulting in models that obey benign requests but refuse harmful ones. While this refusal behavior is widespread across chat models, its…

Machine Learning · Computer Science 2024-11-01 Andy Arditi , Oscar Obeso , Aaquib Syed , Daniel Paleka , Nina Panickssery , Wes Gurnee , Neel Nanda

Large text-to-image models have shown remarkable performance in synthesizing high-quality images. In particular, the subject-driven model makes it possible to personalize the image synthesis for a specific subject, e.g., a human face or an…

Computer Vision and Pattern Recognition · Computer Science 2023-06-14 Yihan Ma , Zhengyu Zhao , Xinlei He , Zheng Li , Michael Backes , Yang Zhang

Despite investments in improving model safety, studies show that misaligned capabilities remain latent in safety-tuned models. In this work, we shed light on the mechanics of this phenomenon. First, we show that even when model generations…

Computation and Language · Computer Science 2024-08-14 Asma Ghandeharioun , Ann Yuan , Marius Guerard , Emily Reif , Michael A. Lepori , Lucas Dixon

Advances in AI-generated content have led to wide adoption of large language models, diffusion-based visual generators, and synthetic audio tools. However, these developments raise critical concerns about misinformation, copyright…

Computation and Language · Computer Science 2025-09-30 Lele Cao

Invisible watermarks safeguard images' copyrights by embedding hidden messages only detectable by owners. They also prevent people from misusing images, especially those generated by AI models. We propose a family of regeneration attacks to…

Cryptography and Security · Computer Science 2024-11-01 Xuandong Zhao , Kexun Zhang , Zihao Su , Saastha Vasan , Ilya Grishchenko , Christopher Kruegel , Giovanni Vigna , Yu-Xiang Wang , Lei Li
‹ Prev 1 2 3 10 Next ›