English
Related papers

Related papers: Linear Adversarial Concept Erasure

200 papers

Consider a dataset of vector-valued observations that consists of noisy inliers, which are explained well by a low-dimensional subspace, along with some number of outliers. This work describes a convex optimization problem, called REAPER,…

Information Theory · Computer Science 2015-07-24 Gilad Lerman , Michael McCoy , Joel A. Tropp , Teng Zhang

Recent advances in generative models have demonstrated remarkable capabilities in producing high-quality images, but their reliance on large-scale unlabeled data has raised significant safety and copyright concerns. Efforts to address these…

Computer Vision and Pattern Recognition · Computer Science 2025-07-21 Yang Zhang , Er Jin , Yanfei Dong , Yixuan Wu , Philip Torr , Ashkan Khakzar , Johannes Stegmaier , Kenji Kawaguchi

Concept Erasure, which aims to prevent pretrained text-to-image models from generating content associated with semantic-harmful concepts (i.e., target concepts), is getting increased attention. State-of-the-art methods formulate this task…

Computer Vision and Pattern Recognition · Computer Science 2025-08-07 Hongxu Chen , Zhen Wang , Taoran Mei , Lin Li , Bowei Zhu , Runshi Li , Long Chen

The ability to control for the kinds of information encoded in neural representation has a variety of use cases, especially in light of the challenge of interpreting these models. We present Iterative Null-space Projection (INLP), a novel…

Computation and Language · Computer Science 2020-04-30 Shauli Ravfogel , Yanai Elazar , Hila Gonen , Michael Twiton , Yoav Goldberg

Concept erasure is extensively utilized in image generation to prevent text-to-image models from generating undesired content. Existing methods can effectively erase narrow concepts that are specific and concrete, such as distinct…

Computer Vision and Pattern Recognition · Computer Science 2026-03-10 Yuze Cai , Jiahao Lu , Hongxiang Shi , Yichao Zhou , Hong Lu

While large-scale text-to-image diffusion models have demonstrated impressive image-generation capabilities, there are significant concerns about their potential misuse for generating unsafe content, violating copyright, and perpetuating…

Computer Vision and Pattern Recognition · Computer Science 2024-05-30 Ruchika Chavhan , Da Li , Timothy Hospedales

Large language models (LLMs) are known to perpetuate stereotypes and exhibit biases. Various strategies have been proposed to mitigate these biases, but most work studies biases as a black-box problem without considering how concepts are…

Computation and Language · Computer Science 2025-09-19 Hannah Cyberey , Yangfeng Ji , David Evans

Neural network models trained on text data have been found to encode undesirable linguistic or sensitive concepts in their representation. Removing such concepts is non-trivial because of a complex relationship between the concept, text…

Machine Learning · Computer Science 2023-06-21 Abhinav Kumar , Chenhao Tan , Amit Sharma

Concept erasure aims to selectively unlearning undesirable content in diffusion models (DMs) to reduce the risk of sensitive content generation. As a novel paradigm in concept erasure, most existing methods employ adversarial training to…

Computer Vision and Pattern Recognition · Computer Science 2025-11-11 Qinghong Yin , Yu Tian , Heming Yang , Xiang Chen , Xianlin Zhang , Xueming Li , Yue Zhan

Dimensionality reduction is an effective method for learning high-dimensional data, which can provide better understanding of decision boundaries in human-readable low-dimensional subspace. Linear methods, such as principal component…

Machine Learning · Computer Science 2020-07-09 Koji Maruhashi , Heewon Park , Rui Yamaguchi , Satoru Miyano

Ensuring fairness in NLP models is crucial, as they often encode sensitive attributes like gender and ethnicity, leading to biased outcomes. Current concept erasure methods attempt to mitigate this by modifying final latent representations…

Computation and Language · Computer Science 2024-10-17 Fanny Jourdan , Louis Béthune , Agustin Picard , Laurent Risser , Nicholas Asher

Vision-language models can encode societal biases and stereotypes, but there are challenges to measuring and mitigating these multimodal harms due to lacking measurement robustness and feature degradation. To address these challenges, we…

Machine Learning · Computer Science 2022-10-27 Hugo Berg , Siobhan Mackenzie Hall , Yash Bhalgat , Wonsuk Yang , Hannah Rose Kirk , Aleksandar Shtedritski , Max Bain

Text-to-image diffusion models have demonstrated the underlying risk of generating various unwanted content, such as sexual elements. To address this issue, the task of concept erasure has been introduced, aiming to erase any undesired…

Computer Vision and Pattern Recognition · Computer Science 2025-06-04 Zheling Meng , Bo Peng , Xiaochuan Jin , Yueming Lyu , Wei Wang , Jing Dong , Tieniu Tan

Machine learning models that first learn a representation of a domain in terms of human-understandable concepts, then use it to make predictions, have been proposed to facilitate interpretation and interaction with models trained on…

Machine Learning · Computer Science 2020-12-08 Isaac Lage , Finale Doshi-Velez

Fine-grained word meaning resolution remains a critical challenge for neural language models (NLMs) as they often overfit to global sentence representations, failing to capture local semantic details. We propose a novel adversarial training…

Computation and Language · Computer Science 2025-11-17 Jader Martins Camboim de Sá , Jooyoung Lee , Cédric Pruski , Marcos Da Silveira

In concept erasure, a model is modified to selectively prevent it from generating a target concept. Despite the rapid development of new methods, it remains unclear how thoroughly these approaches remove the target concept from the model.…

Machine Learning · Computer Science 2025-11-10 Kevin Lu , Nicky Kriplani , Rohit Gandikota , Minh Pham , David Bau , Chinmay Hegde , Niv Cohen

Concept erasure aims to suppress sensitive content in diffusion models, but recent studies show that erased concepts can still be reawakened, revealing vulnerabilities in erasure methods. Existing reawakening methods mainly rely on…

Computer Vision and Pattern Recognition · Computer Science 2026-05-19 Mengyu Sun , Ziyuan Yang , Andrew Beng Jin Teoh , Junxu Liu , Haibo Hu , Yi Zhang

We propose a novel approach to mitigate biases in computer vision models by utilizing counterfactual generation and fine-tuning. While counterfactuals have been used to analyze and address biases in DNN models, the counterfactuals…

Computer Vision and Pattern Recognition · Computer Science 2024-07-01 Pushkar Shukla , Dhruv Srikanth , Lee Cohen , Matthew Turk

Machine learning models often make predictions based on biased features such as gender, race, and other social attributes, posing significant fairness risks, especially in societal applications, such as hiring, banking, and criminal…

Machine Learning · Computer Science 2024-08-28 Yi Zhang , Dongyuan Lu , Jitao Sang

Recent research demonstrates that word embeddings, trained on the human-generated corpus, have strong gender biases in embedding spaces, and these biases can result in the discriminative results from the various downstream tasks. Whereas…

Computation and Language · Computer Science 2020-11-04 Seungjae Shin , Kyungwoo Song , JoonHo Jang , Hyemi Kim , Weonyoung Joo , Il-Chul Moon