English
Related papers

Related papers: Direct Unlearning Optimization for Robust and Safe…

200 papers

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

Text-to-Image (T2I) models have advanced significantly, but their growing popularity raises security concerns due to their potential to generate harmful images. To address these issues, we propose UPAM, a novel framework to evaluate the…

Computer Vision and Pattern Recognition · Computer Science 2025-02-25 Duo Peng , Qiuhong Ke , Mark He Huang , Ping Hu , Jun Liu

Text-to-image (T2I) diffusion models have drawn attention for their ability to generate high-quality images with precise text alignment. However, these models can also be misused to produce inappropriate content. Existing safety measures,…

Computer Vision and Pattern Recognition · Computer Science 2025-10-07 Hongxiang Zhang , Yifeng He , Hao Chen

Machine unlearning (MU) seeks to remove knowledge of specific data samples from trained models without the necessity for complete retraining, a task made challenging by the dual objectives of effective erasure of data and maintaining the…

Machine Learning · Computer Science 2024-07-16 Mark He Huang , Lin Geng Foo , Jun Liu

Text-to-image (T2I) models, though exhibiting remarkable creativity in image generation, can be exploited to produce unsafe images. Existing safety measures, e.g., content moderation or model alignment, fail in the presence of white-box…

Cryptography and Security · Computer Science 2025-10-21 Xinfeng Li , Shengyuan Pang , Jialin Wu , Jiangyi Deng , Huanlong Zhong , Yanjiao Chen , Jie Zhang , Wenyuan Xu

Existing machine unlearning (MU) approaches exhibit significant sensitivity to hyperparameters, requiring meticulous tuning that limits practical deployment. In this work, we first empirically demonstrate the instability and suboptimal…

Machine Learning · Computer Science 2025-11-03 Xuyang Zhong , Haochen Luo , Chen Liu

Post-hoc unlearning has emerged as a practical mechanism for removing undesirable concepts from large text-to-image diffusion models. However, prior work primarily evaluates unlearning through erasure success; its impact on broader…

Computer Vision and Pattern Recognition · Computer Science 2026-04-07 Arian Komaei Koma , Seyed Amir Kasaei , Ali Aghayari , AmirMahdi Sadeghzadeh , Mohammad Hossein Rohban

Text-to-image (T2I) diffusion models have gained widespread application across various domains, demonstrating remarkable creative potential. However, the strong generalization capabilities of these models can inadvertently led they to…

Computer Vision and Pattern Recognition · Computer Science 2025-02-19 Die Chen , Zhiwen Li , Cen Chen , Xiaodan Li , Jinyan Ye

Recent advances in diffusion models have significantly enhanced their ability to generate high-quality images and videos, but they have also increased the risk of producing unsafe content. Existing unlearning/editing-based methods for safe…

Computer Vision and Pattern Recognition · Computer Science 2025-03-17 Jaehong Yoon , Shoubin Yu , Vaidehi Patil , Huaxiu Yao , Mohit Bansal

Text-to-Image (T2I) diffusion/flow models have recently achieved remarkable progress in visual fidelity and text alignment. However, they remain limited when users need to precisely control image layouts, something that natural language…

Computer Vision and Pattern Recognition · Computer Science 2026-04-08 Amadou S. Sangare , Adrien Maglo , Mohamed Chaouch , Bertrand Luvison

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

Text-to-image (T2I) diffusion models have become prominent tools for generating high-fidelity images from text prompts. However, when trained on unfiltered internet data, these models can produce unsafe, incorrect, or stylistically…

Computer Vision and Pattern Recognition · Computer Science 2024-09-11 Rohit Jena , Ali Taghibakhshi , Sahil Jain , Gerald Shen , Nima Tajbakhsh , Arash Vahdat

Text-to-Image (T2I) models have made significant advancements in recent years, but they still struggle to accurately capture intricate details specified in complex compositional prompts. While fine-tuning T2I models with reward objectives…

Computer Vision and Pattern Recognition · Computer Science 2024-11-01 Luca Eyring , Shyamgopal Karthik , Karsten Roth , Alexey Dosovitskiy , Zeynep Akata

In recent years, Text-to-Image (T2I) models have seen remarkable advancements, gaining widespread adoption. However, this progress has inadvertently opened avenues for potential misuse, particularly in generating inappropriate or…

Cryptography and Security · Computer Science 2024-04-02 Yijun Yang , Ruiyuan Gao , Xiaosen Wang , Tsung-Yi Ho , Nan Xu , Qiang Xu

Text-to-image diffusion models rely on massive, web-scale datasets. Training them from scratch is computationally expensive, and as a result, developers often prefer to make incremental updates to existing models. These updates often…

Machine Learning · Computer Science 2025-09-29 Vinith M. Suriyakumar , Rohan Alur , Ayush Sekhari , Manish Raghavan , Ashia C. Wilson

The field of image denoising is currently dominated by discriminative deep learning methods that are trained on pairs of noisy input and clean target images. Recently it has been shown that such methods can also be trained without clean…

Computer Vision and Pattern Recognition · Computer Science 2019-04-08 Alexander Krull , Tim-Oliver Buchholz , Florian Jug

Direct Preference Optimization (DPO) has been proposed as an effective and efficient alternative to reinforcement learning from human feedback (RLHF). However, neither RLHF nor DPO take into account the fact that learning certain…

Computer Vision and Pattern Recognition · Computer Science 2026-02-16 Florinel-Alin Croitoru , Vlad Hondru , Radu Tudor Ionescu , Nicu Sebe , Mubarak Shah

Text guided diffusion models are used by millions of users, but can be easily exploited to produce harmful content. Concept unlearning methods aim at reducing the models' likelihood of generating harmful content. Traditionally, this has…

Artificial Intelligence · Computer Science 2026-02-10 Mansi , Avinash Kori , Francesca Toni , Soteris Demetriou

Previous text-to-image diffusion models typically employ supervised fine-tuning (SFT) to enhance pre-trained base models. However, this approach primarily minimizes the loss of mean squared error (MSE) at the pixel level, neglecting the…

Computer Vision and Pattern Recognition · Computer Science 2025-04-22 Liang Peng , Boxi Wu , Haoran Cheng , Yibo Zhao , Xiaofei He

As Large Language Models (LLMs) demonstrate remarkable capabilities learned from vast corpora, concerns regarding data privacy and safety are receiving increasing attention. LLM unlearning, which aims to remove the influence of specific…

Machine Learning · Computer Science 2025-10-07 Kai Qin , Jiaqi Wu , Jianxiang He , Haoyuan Sun , Yifei Zhao , Bin Liang , Yongzhe Chang , Tiantian Zhang , Houde Liu