English
Related papers

Related papers: Direct Unlearning Optimization for Robust and Safe…

200 papers

Fluoroscopy is critical for real-time X-ray visualization in medical imaging. However, low-dose images are compromised by noise, potentially affecting diagnostic accuracy. Noise reduction is crucial for maintaining image quality, especially…

Image and Video Processing · Electrical Eng. & Systems 2024-11-05 Sun-Young Jeon , Sen Wang , Adam S. Wang , Garry E. Gold , Jang-Hwan Choi

This work introduces Ui2i, a novel model for unpaired image-to-image translation, trained on content-wise unpaired datasets to enable style transfer across domains while preserving content. Building on CycleGAN, Ui2i incorporates key…

Generative multimodal models can exhibit safety failures that are inherently relational: two benign concepts can become unsafe when linked by a specific action or relation (e.g., child-drinking-wine). Existing unlearning and concept-erasure…

Artificial Intelligence · Computer Science 2026-03-26 Vishnu Narayanan Anilkumar , Abhijith Sreesylesh Babu , Trieu Hai Vo , Mohankrishna Kolla , Alexander Cuneo

To obtain a near-optimal policy with fewer interactions in Reinforcement Learning (RL), a promising approach involves the combination of offline RL, which enhances sample efficiency by leveraging offline datasets, and online RL, which…

Machine Learning · Computer Science 2024-11-18 Xiaoyu Wen , Xudong Yu , Rui Yang , Haoyuan Chen , Chenjia Bai , Zhen Wang

LLM unlearning is a technique to remove the impacts of undesirable knowledge from the model without retraining from scratch, which is indispensable towards trustworthy AI. Existing unlearning methods face significant limitations:…

Machine Learning · Computer Science 2026-03-02 Yisheng Zhong , Zhengbang Yang , Zhuangdi Zhu

Copyright law confers upon creators the exclusive rights to reproduce, distribute, and monetize their creative works. However, recent progress in text-to-image generation has introduced formidable challenges to copyright enforcement. These…

Computer Vision and Pattern Recognition · Computer Science 2024-06-24 Rui Ma , Qiang Zhou , Yizhu Jin , Daquan Zhou , Bangjun Xiao , Xiuyu Li , Yi Qu , Aishani Singh , Kurt Keutzer , Jingtong Hu , Xiaodong Xie , Zhen Dong , Shanghang Zhang , Shiji Zhou

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

State-of-the-art Text-to-Image models like Stable Diffusion and DALLE$\cdot$2 are revolutionizing how people generate visual content. At the same time, society has serious concerns about how adversaries can exploit such models to generate…

Computer Vision and Pattern Recognition · Computer Science 2023-08-17 Yiting Qu , Xinyue Shen , Xinlei He , Michael Backes , Savvas Zannettou , Yang Zhang

Recent text-to-image (T2I) models have benefited from large-scale and high-quality data, demonstrating impressive performance. However, these T2I models still struggle to produce images that are aesthetically pleasing, geometrically…

Computer Vision and Pattern Recognition · Computer Science 2024-03-28 Jianshu Guo , Wenhao Chai , Jie Deng , Hsiang-Wei Huang , Tian Ye , Yichen Xu , Jiawei Zhang , Jenq-Neng Hwang , Gaoang Wang

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

Unsupervised text style transfer aims to transfer the underlying style of text but keep its main content unchanged without parallel data. Most existing methods typically follow two steps: first separating the content from the original…

Computation and Language · Computer Science 2019-05-27 Fuli Luo , Peng Li , Jie Zhou , Pengcheng Yang , Baobao Chang , Zhifang Sui , Xu Sun

Text-to-image models have shown remarkable capabilities in generating high-quality images from natural language descriptions. However, these models are highly vulnerable to adversarial prompts, which can bypass safety measures and produce…

Cryptography and Security · Computer Science 2025-10-16 Peigui Qi , Kunsheng Tang , Wenbo Zhou , Weiming Zhang , Nenghai Yu , Tianwei Zhang , Qing Guo , Jie Zhang

Large-scale text-to-image generative models have shown remarkable ability to synthesize diverse and high-quality images. However, it is still challenging to directly apply these models for editing real images for two reasons. First, it is…

Computer Vision and Pattern Recognition · Computer Science 2025-08-19 Syed Muhmmad Israr , Feng Zhao

Text-to-image diffusion models (T2I DMs) have achieved remarkable success in generating high-quality and diverse images from text prompts, yet recent studies have revealed their vulnerability to backdoor attacks. Existing attack methods…

Cryptography and Security · Computer Science 2025-08-05 Haoran Dai , Jiawen Wang , Ruo Yang , Manali Sharma , Zhonghao Liao , Yuan Hong , Binghui Wang

Recently, denoising diffusion models have achieved promising results in 2D image generation and editing. Instruct-NeRF2NeRF (IN2N) introduces the success of diffusion into 3D scene editing through an "Iterative dataset update" (IDU)…

Computer Vision and Pattern Recognition · Computer Science 2025-02-25 Yuxuan Xiong , Yue Shi , Yishun Dou , Bingbing Ni

Machine unlearning for text-to-image diffusion models aims to selectively remove undesirable concepts from pre-trained models without costly retraining. Current unlearning methods share a common weakness: erased concepts return when the…

Computer Vision and Pattern Recognition · Computer Science 2026-04-24 Aljalila Aladawi , Mohammed Talha Alam , Fakhri Karray

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

Modern over-parameterized deep models are highly data-dependent, with large scale general-purpose and domain-specific datasets serving as the bedrock for rapid advancements. However, many datasets are proprietary or contain sensitive…

Computer Vision and Pattern Recognition · Computer Science 2025-08-05 Hongyu Zhu , Sichu Liang , Wenwen Wang , Zhuomeng Zhang , Fangqi Li , Shi-Lin Wang

Recent works have demonstrated that using reinforcement learning (RL) with multiple quality rewards can improve the quality of generated images in text-to-image (T2I) generation. However, manually adjusting reward weights poses challenges…

Computer Vision and Pattern Recognition · Computer Science 2024-07-16 Seung Hyun Lee , Yinxiao Li , Junjie Ke , Innfarn Yoo , Han Zhang , Jiahui Yu , Qifei Wang , Fei Deng , Glenn Entis , Junfeng He , Gang Li , Sangpil Kim , Irfan Essa , Feng Yang

Image-to-image translation has drawn great attention during the past few years. It aims to translate an image in one domain to a given reference image in another domain. Due to its effectiveness and efficiency, many applications can be…

Computer Vision and Pattern Recognition · Computer Science 2019-11-05 Weihao Xia , Yujiu Yang , Jing-Hao Xue