English
Related papers

Related papers: Pruning for Robust Concept Erasing in Diffusion Mo…

200 papers

Recent developments in text-to-image models, particularly Stable Diffusion, have marked significant achievements in various applications. With these advancements, there are growing safety concerns about the vulnerability of the model that…

Computer Vision and Pattern Recognition · Computer Science 2024-01-18 Chenyu Zhang , Lanjun Wang , Anan Liu

Recurrent Neural Network (RNN) has been widely used to tackle a wide variety of language generation problems and are capable of attaining state-of-the-art (SOTA) performance. However despite its impressive results, the large number of…

Computer Vision and Pattern Recognition · Computer Science 2019-10-29 Jia Huei Tan , Chee Seng Chan , Joon Huang Chuah

The rapid proliferation of large-scale text-to-image diffusion (T2ID) models has raised serious concerns about their potential misuse in generating harmful content. Although numerous methods have been proposed for erasing undesired concepts…

Computer Vision and Pattern Recognition · Computer Science 2025-04-03 Koushik Srivatsan , Fahad Shamshad , Muzammal Naseer , Vishal M. Patel , Karthik Nandakumar

The vulnerability of deep neural networks against adversarial examples - inputs with small imperceptible perturbations - has gained a lot of attention in the research community recently. Simultaneously, the number of parameters of…

Machine Learning · Computer Science 2021-08-20 Florian Merkle , Maximilian Samsinger , Pascal Schöttle

Neural networks have achieved remarkable performance across a wide range of tasks, yet they remain susceptible to adversarial perturbations, which pose significant risks in safety-critical applications. With the rise of multimodality,…

Computer Vision and Pattern Recognition · Computer Science 2024-10-21 Xinxin Liu , Zhongliang Guo , Siyuan Huang , Chun Pong Lau

Denoising diffusion models have emerged as a powerful tool for various image generation and editing tasks, facilitating the synthesis of visual content in an unconditional or input-conditional manner. The core idea behind them is learning…

Computer Vision and Pattern Recognition · Computer Science 2025-03-12 Yi Huang , Jiancheng Huang , Yifan Liu , Mingfu Yan , Jiaxi Lv , Jianzhuang Liu , Wei Xiong , He Zhang , Liangliang Cao , Shifeng Chen

Modern neural models trained on textual data rely on pre-trained representations that emerge without direct supervision. As these representations are increasingly being used in real-world applications, the inability to \emph{control} their…

Machine Learning · Computer Science 2024-12-18 Shauli Ravfogel , Michael Twiton , Yoav Goldberg , Ryan Cotterell

Recent advancements in large-scale generative models have enabled the creation of high-quality images and videos, but have also raised significant safety concerns regarding the generation of unsafe content. To mitigate this, concept erasure…

Computer Vision and Pattern Recognition · Computer Science 2025-11-26 Viet Nguyen , Vishal M. Patel

Concept erasure is the task of erasing information about a concept (e.g., gender or race) from a representation set while retaining the maximum possible utility -- information from original representations. Concept erasure is useful in…

Diffusion models have achieved remarkable progress in the field of image generation due to their outstanding capabilities. However, these models require substantial computing resources because of the multi-step denoising process during…

Computer Vision and Pattern Recognition · Computer Science 2024-10-23 Haowei Zhu , Dehua Tang , Ji Liu , Mingjie Lu , Jintu Zheng , Jinzhang Peng , Dong Li , Yu Wang , Fan Jiang , Lu Tian , Spandan Tiwari , Ashish Sirasao , Jun-Hai Yong , Bin Wang , Emad Barsoum

The personalization techniques of diffusion models succeed in generating images with specific concepts. This ability also poses great threats to copyright protection and network security since malicious users can generate unauthorized…

Cryptography and Security · Computer Science 2025-08-26 Liangqi Lei , Keke Gai , Jing Yu , Liehuang Zhu , Qi Wu

Concept unlearning in diffusion models is hampered by feature splitting, where concepts are distributed across many latent features, making their removal challenging and computationally expensive. We introduce SAEmnesia, a supervised sparse…

Computer Vision and Pattern Recognition · Computer Science 2025-12-01 Enrico Cassano , Riccardo Renzulli , Marco Nurisso , Mirko Zaffaroni , Alan Perotti , Marco Grangetto

Motivated by ethical and legal concerns, the scientific community is actively developing methods to limit the misuse of Text-to-Image diffusion models for reproducing copyrighted, violent, explicit, or personal information in the generated…

Computer Vision and Pattern Recognition · Computer Science 2024-04-23 Vitali Petsiuk , Kate Saenko

The recent advances in diffusion models (DMs) have revolutionized the generation of realistic and complex images. However, these models also introduce potential safety hazards, such as producing harmful content and infringing data…

Computer Vision and Pattern Recognition · Computer Science 2024-07-09 Yimeng Zhang , Jinghan Jia , Xin Chen , Aochuan Chen , Yihua Zhang , Jiancheng Liu , Ke Ding , Sijia Liu

Erasing specific concepts from text-to-image diffusion models is essential for avoiding the generation of copyrighted and explicit content. Closed-form concept erasure methods offer a fast alternative to backpropagation-based techniques,…

Machine Learning · Computer Science 2026-05-12 Nicola Novello , Andrea M. Tonello

Concept unlearning aims to erase a target concept from a pretrained text-to-image diffusion model without retraining. Closed-form methods are attractive in this setting because they apply a single deterministic edit to the cross-attention…

Computer Vision and Pattern Recognition · Computer Science 2026-05-26 Saemi Moon , Suhyeon Jun , Seoyeon Lee , Dongwoo Kim

The success of diffusion models has raised concerns about the generation of unsafe or harmful content, prompting concept erasure approaches that fine-tune modules to suppress specific concepts while preserving general generative…

Computer Vision and Pattern Recognition · Computer Science 2026-01-08 Jiahang Tu , Ye Li , Yiming Wu , Hanbin Zhao , Chao Zhang , Hui Qian

Deep Learning models have become the dominant approach in several areas due to their high performance. Unfortunately, the size and hence computational requirements of operating such models can be considerably high. Therefore, this…

Computer Vision and Pattern Recognition · Computer Science 2019-12-04 Abdullah Salama , Oleksiy Ostapenko , Tassilo Klein , Moin Nabi

Diffusion models (DMs) have achieved significant progress in text-to-image generation. However, the inevitable inclusion of sensitive information during pre-training poses safety risks, such as unsafe content generation and copyright…

Computer Vision and Pattern Recognition · Computer Science 2025-06-12 Hongguang Zhu , Yunchao Wei , Mengyu Wang , Siyu Jiao , Yan Fang , Jiannan Huang , Yao Zhao

Large-scale text-to-image (T2I) diffusion models have achieved remarkable generative performance about various concepts. With the limitation of privacy and safety in practice, the generative capability concerning NSFW (Not Safe For Work)…

Computer Vision and Pattern Recognition · Computer Science 2025-10-01 Jiahang Tu , Qian Feng , Jiahua Dong , Hanbin Zhao , Chao Zhang , Nicu Sebe , Hui Qian