Related papers: TaCo: Targeted Concept Erasure Prevents Non-Linear…

Recent work has explored how to train machine learning models which do not discriminate against any subgroup of the population as determined by sensitive attributes such as gender or race. To avoid disparate treatment, sensitive attributes…

Concept erasure in text-to-image diffusion models aims to disable pre-trained diffusion models from generating images related to a target concept. To perform reliable concept erasure, the properties of robustness and locality are desirable.…

One of the pursued objectives of deep learning is to provide tools that learn abstract representations of reality from the observation of multiple contextual situations. More precisely, one wishes to extract disentangled representations…

Methods for erasing human-interpretable concepts from neural representations that assume linearity have been found to be tractable and useful. However, the impact of this removal on the behavior of downstream classifiers trained on the…

We address the problem of concept removal in deep neural networks, aiming to learn representations that do not encode certain specified concepts (e.g., gender etc.) We propose a novel method based on adversarial linear classifiers trained…

Text-to-Image (T2I) models have made remarkable progress in generating high-quality, diverse visual content from natural language prompts. However, their ability to reproduce copyrighted styles, sensitive imagery, and harmful content raises…

Existing concept erasure methods for text-to-image diffusion models commonly rely on fixed anchor strategies, which often lead to critical issues such as concept re-emergence and erosion. To address this, we conduct causal tracing to reveal…

Concept erasure aims to remove specified features from an embedding. It can improve fairness (e.g. preventing a classifier from using gender or race) and interpretability (e.g. removing a concept to observe changes in model behavior). We…

Text-to-image diffusion models have shown unprecedented generative capability, but their ability to produce undesirable concepts (e.g.~pornographic content, sensitive identities, copyrighted styles) poses serious concerns for privacy,…

Text-to-image generative models can produce photo-realistic images for an extremely broad range of concepts, and their usage has proliferated widely among the general public. On the flip side, these models have numerous drawbacks, including…

To what extent does concept erasure eliminate generative capacity in diffusion models? While prior evaluations have primarily focused on measuring concept suppression under specific textual prompts, we explore a complementary and…

Recent advance in text-to-image diffusion models have significantly facilitated the generation of high-quality images, but also raising concerns about the illegal creation of harmful content, such as copyrighted images. Existing concept…

Machine learning models are extensively being used to make decisions that have a significant impact on human life. These models are trained over historical data that may contain information about sensitive attributes such as race, sex,…

The emergence of large-scale pretrained language models has posed unprecedented challenges in deriving explanations of why the model has made some predictions. Stemmed from the compositional nature of languages, spurious correlations have…

Modern neural networks often encode unwanted concepts alongside task-relevant information, leading to fairness and interpretability concerns. Existing post-hoc approaches can remove undesired concepts but often degrade useful signals. We…

Optimizing NLP models for fairness poses many challenges. Lack of differentiable fairness measures prevents gradient-based loss training or requires surrogate losses that diverge from the true metric of interest. In addition, competing…

As text-to-image diffusion models grow increasingly prevalent, the ability to remove specific concepts-mostly explicit content and many copyrighted characters or styles-has become essential for safety and compliance. Existing unlearning…

Text-to-Image models such as Stable Diffusion have shown impressive image generation synthesis, thanks to the utilization of large-scale datasets. However, these datasets may contain sexually explicit, copyrighted, or undesirable content,…

The exceptional generative capability of text-to-image models has raised substantial safety concerns regarding the generation of Not-Safe-For-Work (NSFW) content and potential copyright infringement. To address these concerns, previous…

State-of-the-art NLP methods achieve human-like performance on many tasks, but make errors nevertheless. Characterizing these errors in easily interpretable terms gives insight into whether a classifier is prone to making systematic errors,…