Prompt-Driven and Training-Free Forgetting Approach and Dataset for Large Language Models

• URL: http://arxiv.org/abs/2504.12574v1
• Date: Thu, 17 Apr 2025 01:44:57 GMT
• Title: Prompt-Driven and Training-Free Forgetting Approach and Dataset for Large Language Models
• Authors: Zhenyu Yu, Mohd Yamani Inda Idris, Pei Wang,
• Abstract summary: We propose an Automatic dataset Creation Framework based on prompt-based layered editing and training-free local feature removal.<n>The ForgetMe dataset encompasses a diverse set of real and synthetic scenarios, including CUB-200-2011 (Birds), Stanford-Dogs, ImageNet, and a synthetic cat dataset.<n>We apply LoRA fine-tuning on Stable Diffusion to achieve selective unlearning on this dataset and validate the effectiveness of both the ForgetMe dataset and the Entangled metric.
• Score: 4.824120664293887
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The widespread adoption of diffusion models in image generation has increased the demand for privacy-compliant unlearning. However, due to the high-dimensional nature and complex feature representations of diffusion models, achieving selective unlearning remains challenging, as existing methods struggle to remove sensitive information while preserving the consistency of non-sensitive regions. To address this, we propose an Automatic Dataset Creation Framework based on prompt-based layered editing and training-free local feature removal, constructing the ForgetMe dataset and introducing the Entangled evaluation metric. The Entangled metric quantifies unlearning effectiveness by assessing the similarity and consistency between the target and background regions and supports both paired (Entangled-D) and unpaired (Entangled-S) image data, enabling unsupervised evaluation. The ForgetMe dataset encompasses a diverse set of real and synthetic scenarios, including CUB-200-2011 (Birds), Stanford-Dogs, ImageNet, and a synthetic cat dataset. We apply LoRA fine-tuning on Stable Diffusion to achieve selective unlearning on this dataset and validate the effectiveness of both the ForgetMe dataset and the Entangled metric, establishing them as benchmarks for selective unlearning. Our work provides a scalable and adaptable solution for advancing privacy-preserving generative AI.

Related papers

• CHASe: Client Heterogeneity-Aware Data Selection for Effective Federated Active Learning [22.38403602956309]
  We propose CHASe (Client Heterogeneity-Aware Data Selection), specifically designed for Federated Active Learning (FAL) CHASe focuses on identifying those unlabeled samples with high epistemic variations (EVs), which notably oscillate around the decision boundaries during training. Experiments show that CHASe surpasses various established baselines in terms of effectiveness and efficiency, validated across diverse datasets, model complexities, and heterogeneous federation settings.
  arXiv  Detail & Related papers  (2025-04-24T11:28:00Z)
• Improving the Efficiency of Self-Supervised Adversarial Training through Latent Clustering-Based Selection [2.7554677967598047]
  adversarially robust learning is widely recognized to demand significantly more training examples.<n>Recent works propose the use of self-supervised adversarial training with external or synthetically generated unlabeled data to enhance model robustness.<n>We propose novel methods to strategically select a small subset of unlabeled data essential for SSAT and robustness improvement.
  arXiv  Detail & Related papers  (2025-01-15T15:47:49Z)
• Web-Scale Visual Entity Recognition: An LLM-Driven Data Approach [56.55633052479446]
  Web-scale visual entity recognition presents significant challenges due to the lack of clean, large-scale training data. We propose a novel methodology to curate such a dataset, leveraging a multimodal large language model (LLM) for label verification, metadata generation, and rationale explanation. Experiments demonstrate that models trained on this automatically curated data achieve state-of-the-art performance on web-scale visual entity recognition tasks.
  arXiv  Detail & Related papers  (2024-10-31T06:55:24Z)
• A Plug-and-Play Method for Rare Human-Object Interactions Detection by Bridging Domain Gap [50.079224604394]
  We present a novel model-agnostic framework called textbfContext-textbfEnhanced textbfFeature textbfAment (CEFA) CEFA consists of a feature alignment module and a context enhancement module. Our method can serve as a plug-and-play module to improve the detection performance of HOI models on rare categories.
  arXiv  Detail & Related papers  (2024-07-31T08:42:48Z)
• Partially Blinded Unlearning: Class Unlearning for Deep Networks a Bayesian Perspective [4.31734012105466]
  Machine Unlearning is the process of selectively discarding information designated to specific sets or classes of data from a pre-trained model. We propose a methodology tailored for the purposeful elimination of information linked to a specific class of data from a pre-trained classification network. Our novel approach, termed textbfPartially-Blinded Unlearning (PBU), surpasses existing state-of-the-art class unlearning methods, demonstrating superior effectiveness.
  arXiv  Detail & Related papers  (2024-03-24T17:33:22Z)
• The Frontier of Data Erasure: Machine Unlearning for Large Language Models [56.26002631481726]
  Large Language Models (LLMs) are foundational to AI advancements. LLMs pose risks by potentially memorizing and disseminating sensitive, biased, or copyrighted information. Machine unlearning emerges as a cutting-edge solution to mitigate these concerns.
  arXiv  Detail & Related papers  (2024-03-23T09:26:15Z)
• Enhancing Information Maximization with Distance-Aware Contrastive Learning for Source-Free Cross-Domain Few-Shot Learning [55.715623885418815]
  Cross-Domain Few-Shot Learning methods require access to source domain data to train a model in the pre-training phase. Due to increasing concerns about data privacy and the desire to reduce data transmission and training costs, it is necessary to develop a CDFSL solution without accessing source data. This paper proposes an Enhanced Information Maximization with Distance-Aware Contrastive Learning method to address these challenges.
  arXiv  Detail & Related papers  (2024-03-04T12:10:24Z)
• Integrating kNN with Foundation Models for Adaptable and Privacy-Aware Image Classification [0.13108652488669734]
  Traditional deep learning models implicity encode knowledge limiting their transparency and ability to adapt to data changes. We address this limitation by storing embeddings of the underlying training data independently of the model weights. Our approach integrates the $k$-Nearest Neighbor ($k$-NN) classifier with a vision-based foundation model, pre-trained self-supervised on natural images.
  arXiv  Detail & Related papers  (2024-02-19T20:08:13Z)
• Erasing Undesirable Influence in Diffusion Models [51.225365010401006]
  Diffusion models are highly effective at generating high-quality images but pose risks, such as the unintentional generation of NSFW (not safe for work) content. In this work, we introduce EraseDiff, an algorithm designed to preserve the utility of the diffusion model on retained data while removing the unwanted information associated with the data to be forgotten.
  arXiv  Detail & Related papers  (2024-01-11T09:30:36Z)
• From Zero to Hero: Detecting Leaked Data through Synthetic Data Injection and Model Querying [10.919336198760808]
  We introduce a novel methodology to detect leaked data that are used to train classification models. textscLDSS involves injecting a small volume of synthetic data--characterized by local shifts in class distribution--into the owner's dataset. This enables the effective identification of models trained on leaked data through model querying alone.
  arXiv  Detail & Related papers  (2023-10-06T10:36:28Z)
• Fusing Pseudo Labels with Weak Supervision for Dynamic Traffic Scenarios [0.0]
  We introduce a weakly-supervised label unification pipeline that amalgamates pseudo labels from object detection models trained on heterogeneous datasets. Our pipeline engenders a unified label space through the amalgamation of labels from disparate datasets, rectifying bias and enhancing generalization. We retrain a solitary object detection model using the merged label space, culminating in a resilient model proficient in dynamic traffic scenarios.
  arXiv  Detail & Related papers  (2023-08-30T11:33:07Z)
• Cluster-level pseudo-labelling for source-free cross-domain facial expression recognition [94.56304526014875]
  We propose the first Source-Free Unsupervised Domain Adaptation (SFUDA) method for Facial Expression Recognition (FER) Our method exploits self-supervised pretraining to learn good feature representations from the target data. We validate the effectiveness of our method in four adaptation setups, proving that it consistently outperforms existing SFUDA methods when applied to FER.
  arXiv  Detail & Related papers  (2022-10-11T08:24:50Z)
• Salient Objects in Clutter [130.63976772770368]
  This paper identifies and addresses a serious design bias of existing salient object detection (SOD) datasets. This design bias has led to a saturation in performance for state-of-the-art SOD models when evaluated on existing datasets. We propose a new high-quality dataset and update the previous saliency benchmark.
  arXiv  Detail & Related papers  (2021-05-07T03:49:26Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.