English
Related papers

Related papers: Enhancing Diffusion-based Unrestricted Adversarial…

200 papers

Diffusion models have achieved outstanding image generation by reversing a forward noising process to approximate true data distributions. During training, these models predict diffusion scores from noised versions of true samples in a…

Computer Vision and Pattern Recognition · Computer Science 2025-04-16 Dazhong Shen , Guanglu Song , Yi Zhang , Bingqi Ma , Lujundong Li , Dongzhi Jiang , Zhuofan Zong , Yu Liu

In recent years, diffusion models (DMs) have drawn significant attention for their success in approximating data distributions, yielding state-of-the-art generative results. Nevertheless, the versatility of these models extends beyond their…

Computer Vision and Pattern Recognition · Computer Science 2024-03-19 Peter Lorenz , Ricard Durall , Janis Keuper

Direct preference optimization (DPO) methods have shown strong potential in aligning text-to-image diffusion models with human preferences by training on paired comparisons. These methods improve training stability by avoiding the REINFORCE…

Computer Vision and Pattern Recognition · Computer Science 2025-10-22 Yi-Lun Wu , Bo-Kai Ruan , Chiang Tseng , Hong-Han Shuai

Due to their powerful image generation capabilities, diffusion-based adversarial example generation methods through image editing are rapidly gaining popularity. However, due to reliance on the discriminative capability of the diffusion…

Computer Vision and Pattern Recognition · Computer Science 2025-07-01 Gaozheng Pei , Ke Ma , Dongpeng Zhang , Chengzhi Sun , Qianqian Xu , Qingming Huang

Despite remarkable achievements in deep learning across various domains, its inherent vulnerability to adversarial examples still remains a critical concern for practical deployment. Adversarial training has emerged as one of the most…

Machine Learning · Computer Science 2024-11-06 Junhao Dong , Xinghua Qu , Z. Jane Wang , Yew-Soon Ong

Recent studies have demonstrated significant progress in aligning text-to-image diffusion models with human preference via Reinforcement Learning from Human Feedback. However, while existing methods achieve high scores on automated reward…

Computer Vision and Pattern Recognition · Computer Science 2026-03-11 Chubin Chen , Sujie Hu , Jiashu Zhu , Meiqi Wu , Jintao Chen , Yanxun Li , Nisha Huang , Chengyu Fang , Jiahong Wu , Xiangxiang Chu , Xiu Li

Direct Preference Optimization (DPO) has shown promising results in aligning generative outputs with human preferences by distinguishing between chosen and rejected samples. However, a critical limitation of DPO is likelihood displacement,…

Computer Vision and Pattern Recognition · Computer Science 2025-11-25 Ruojun Xu , Yu Kai , Xuhua Ren , Jiaxiang Cheng , Bing Ma , Tianxiang Zheng , Qinhlin Lu

In this work, we focus on the alignment problem of diffusion models with a continuous reward function, which represents specific objectives for downstream tasks, such as increasing darkness or improving the aesthetics of images. The central…

Machine Learning · Computer Science 2024-10-03 Zhiwei Tang , Jiangweizhi Peng , Jiasheng Tang , Mingyi Hong , Fan Wang , Tsung-Hui Chang

This work addresses the challenge of personalizing trajectories generated in automated decision-making systems by introducing a resource-efficient approach that enables rapid adaptation to individual users' preferences. Our method leverages…

Machine Learning · Computer Science 2025-03-25 Wen Zheng Terence Ng , Jianda Chen , Yuan Xu , Tianwei Zhang

We introduce a new attack paradigm that embeds hidden adversarial capabilities directly into diffusion models via fine-tuning, without altering their observable behavior or requiring modifications during inference. Unlike prior approaches…

Machine Learning · Computer Science 2025-04-15 Lucas Beerens , Desmond J. Higham

RLHF techniques like DPO can significantly improve the generation quality of text-to-image diffusion models. However, these methods optimize for a single reward that aligns model generation with population-level preferences, neglecting the…

Machine Learning · Computer Science 2025-01-14 Meihua Dang , Anikait Singh , Linqi Zhou , Stefano Ermon , Jiaming Song

Diffusion models generate highly realistic images but often struggle with precise text-image alignment. While recent post-training methods improve alignment using external rewards or human preference signals, their performance heavily…

Machine Learning · Computer Science 2026-05-29 Jaa-Yeon Lee , Yeobin Hong , Taesung Kwon , Jong Chul Ye

Diffusion models are state-of-the-art generative models, yet their samples often fail to satisfy application objectives such as safety constraints or domain-specific validity. Existing techniques for alignment require gradients, internal…

Adversarial training and adversarial purification are two widely used defense strategies for enhancing model robustness against adversarial attacks. However, adversarial training requires costly retraining, while adversarial purification…

Computer Vision and Pattern Recognition · Computer Science 2025-09-17 Xuelong Dai , Dong Wang , Xiuzhen Cheng , Bin Xiao

Preference optimization for diffusion models aims to align them with human preferences for images. Previous methods typically use Vision-Language Models (VLMs) as pixel-level reward models to approximate human preferences. However, when…

Computer Vision and Pattern Recognition · Computer Science 2025-10-03 Tao Zhang , Cheng Da , Kun Ding , Huan Yang , Kun Jin , Yan Li , Tingting Gao , Di Zhang , Shiming Xiang , Chunhong Pan

Diffusion models have achieved remarkable success in sequential decision-making by leveraging the highly expressive model capabilities in policy learning. A central problem for learning diffusion policies is to align the policy output with…

Machine Learning · Computer Science 2024-12-17 Zhao Shan , Chenyou Fan , Shuang Qiu , Jiyuan Shi , Chenjia Bai

Aligning diffusion models with user preferences has been a key challenge. Existing methods for aligning diffusion models either require retraining or are limited to differentiable reward functions. To address these limitations, we propose a…

Computer Vision and Pattern Recognition · Computer Science 2025-02-28 Po-Hung Yeh , Kuang-Huei Lee , Jun-Cheng Chen

Reinforcement learning from human feedback (RLHF) has been popular for aligning text-to-image (T2I) diffusion models with human preferences. As a mainstream branch of RLHF, Direct Preference Optimization (DPO) offers a computationally…

Machine Learning · Computer Science 2026-05-07 Jiaming Hu , Jiamu Bai , Haoyu Wang , Debarghya Mukherjee , Ioannis Ch. Paschalidis

Denoising diffusion models have shown remarkable potential in various generation tasks. The open-source large-scale text-to-image model, Stable Diffusion, becomes prevalent as it can generate realistic artistic or facial images with…

Computer Vision and Pattern Recognition · Computer Science 2023-05-09 Ruijia Wu , Yuhang Wang , Huafeng Shi , Zhipeng Yu , Yichao Wu , Ding Liang

Diffusion models have become prevalent in generative modeling due to their ability to sample from complex distributions. To improve the quality of generated samples and their compliance with user requirements, two commonly used methods are:…

Machine Learning · Computer Science 2025-12-01 Shervin Khalafi , Ignacio Hounie , Dongsheng Ding , Alejandro Ribeiro