Targeted Unlearning with Single Layer Unlearning Gradient

• URL: http://arxiv.org/abs/2407.11867v3
• Date: Thu, 29 May 2025 18:24:25 GMT
• Title: Targeted Unlearning with Single Layer Unlearning Gradient
• Authors: Zikui Cai, Yaoteng Tan, M. Salman Asif,
• Abstract summary: Machine unlearning methods aim to remove sensitive or unwanted content from trained models.<n>We propose Single Layer Unlearning Gradient computation (SLUG) as an efficient method to unlearn targeted information.
• Score: 15.374381635334897
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Machine unlearning methods aim to remove sensitive or unwanted content from trained models, but typically demand extensive model updates at significant computational cost while potentially degrading model performance on both related and unrelated tasks. We propose Single Layer Unlearning Gradient (SLUG) as an efficient method to unlearn targeted information by updating a single critical layer using a one-time gradient computation. SLUG uses layer importance and gradient alignment metrics to identify the optimal layer for targeted information removal while preserving the model utility. We demonstrate the effectiveness of SLUG for CLIP, Stable Diffusion, and vision-language models (VLMs) in removing concrete (e.g., identities and objects) and abstract concepts (e.g., artistic styles). On the UnlearnCanvas benchmark, SLUG achieves comparable unlearning performance to existing methods while requiring significantly less computational resources. Our proposed approach offers a practical solution for targeted unlearning that is computationally efficient and precise. Our code is available at https://github.com/CSIPlab/SLUG.

Related papers

• Efficient Machine Unlearning via Influence Approximation [75.31015485113993]
  Influence-based unlearning has emerged as a prominent approach to estimate the impact of individual training samples on model parameters without retraining.<n>This paper establishes a theoretical link between memorizing (incremental learning) and forgetting (unlearning)<n>We introduce the Influence Approximation Unlearning algorithm for efficient machine unlearning from the incremental perspective.
  arXiv  Detail & Related papers  (2025-07-31T05:34:27Z)
• Information Retrieval in the Age of Generative AI: The RGB Model [77.96475639967431]
  This paper presents a novel quantitative approach to shed light on the complex information dynamics arising from the growing use of generative AI tools. We propose a model to characterize the generation, indexing, and dissemination of information in response to new topics. Our findings suggest that the rapid pace of generative AI adoption, combined with increasing user reliance, can outpace human verification, escalating the risk of inaccurate information proliferation.
  arXiv  Detail & Related papers  (2025-04-29T10:21:40Z)
• Privacy Preservation in Gen AI Applications [0.0]
  Large Language Models (LLMs) may unintentionally absorb and reveal Personally Identifiable Information (PII) from user interactions. Deep neural networks' intricacy makes it difficult to track down or stop the inadvertent storing and release of private information. This study tackles these issues by detecting Generative AI weaknesses through attacks such as data extraction, model inversion, and membership inference. It ensures privacy without sacrificing functionality by using methods to identify, alter, or remove PII before to dealing with LLMs.
  arXiv  Detail & Related papers  (2025-04-12T06:19:37Z)
• Optimizing ML Training with Metagradient Descent [69.89631748402377]
  We introduce an algorithm for efficiently calculating metagradients -- gradients through model training -- at scale.<n>We then introduce a "smooth model training" framework that enables effective optimization using metagradients.
  arXiv  Detail & Related papers  (2025-03-17T22:18:24Z)
• LESA: Learnable LLM Layer Scaling-Up [57.0510934286449]
  Training Large Language Models (LLMs) from scratch requires immense computational resources, making it prohibitively expensive.<n>Model scaling-up offers a promising solution by leveraging the parameters of smaller models to create larger ones.<n>We propose textbfLESA, a novel learnable method for depth scaling-up.
  arXiv  Detail & Related papers  (2025-02-19T14:58:48Z)
• Technical Report for the Forgotten-by-Design Project: Targeted Obfuscation for Machine Learning [0.03749861135832072]
  This paper explores the concept of the Right to be Forgotten (RTBF) within AI systems, contrasting it with traditional data erasure methods. We introduce Forgotten by Design, a proactive approach to privacy preservation that integrates instance-specific obfuscation techniques. Our experiments on the CIFAR-10 dataset demonstrate that our techniques reduce privacy risks by at least an order of magnitude while maintaining model accuracy.
  arXiv  Detail & Related papers  (2025-01-20T15:07:59Z)
• Multi-Objective Large Language Model Unlearning [3.372396620898397]
  Gradient Ascent (GA) is a proactive way to decrease the prediction probability of the model on the target data.<n>We propose Multi-Objective Large Language Model Unlearning (MOLLM) algorithm to overcome gradient explosion and catastrophic forgetting.<n>Our empirical results verify that MoLLM outperforms the SOTA GA-based LLM unlearning methods in terms of unlearning effect and model utility preservation.
  arXiv  Detail & Related papers  (2024-12-29T09:35:56Z)
• Machine Unlearning Doesn't Do What You Think: Lessons for Generative AI Policy, Research, and Practice [186.055899073629]
  Unlearning is often invoked as a solution for removing the effects of targeted information from a generative-AI model. Unlearning is also proposed as a way to prevent a model from generating targeted types of information in its outputs. Both of these goals--the targeted removal of information from a model and the targeted suppression of information from a model's outputs--present various technical and substantive challenges.
  arXiv  Detail & Related papers  (2024-12-09T20:18:43Z)
• Game-Theoretic Machine Unlearning: Mitigating Extra Privacy Leakage [12.737028324709609]
  Recent legislation obligates organizations to remove requested data and its influence from a trained model. We propose a game-theoretic machine unlearning algorithm that simulates the competitive relationship between unlearning performance and privacy protection.
  arXiv  Detail & Related papers  (2024-11-06T13:47:04Z)
• Learn while Unlearn: An Iterative Unlearning Framework for Generative Language Models [49.043599241803825]
  Iterative Contrastive Unlearning (ICU) framework consists of three core components. A Knowledge Unlearning Induction module removes specific knowledge through an unlearning loss. A Contrastive Learning Enhancement module to preserve the model's expressive capabilities against the pure unlearning goal. And an Iterative Unlearning Refinement module that dynamically assess the unlearning extent on specific data pieces and make iterative update.
  arXiv  Detail & Related papers  (2024-07-25T07:09:35Z)
• Towards Efficient Target-Level Machine Unlearning Based on Essential Graph [18.35868679190816]
  Existing studies of machine unlearning mainly focus on unlearning requests that forget a cluster of instances or all instances from one class. We propose a more effective and efficient unlearning scheme that focuses on removing partial targets from the model. Experiments with different training models on various datasets demonstrate the effectiveness of the proposed approach.
  arXiv  Detail & Related papers  (2024-06-16T14:17:13Z)
• A More Practical Approach to Machine Unlearning [0.0]
  Machine unlearning is the ability to remove the influence of specific data points from a trained model. The embedding layer in GPT-2 is crucial for effective unlearning. Fuzzy matching techniques shift the model to a new optimum, while iterative unlearning provides a more complete modality.
  arXiv  Detail & Related papers  (2024-06-13T17:59:06Z)
• 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)
• Generative Models are Self-Watermarked: Declaring Model Authentication through Re-Generation [17.88043926057354]
  verifying data ownership poses formidable challenges, particularly in cases of unauthorized reuse of generated data. Our work is dedicated to detecting data reuse from even an individual sample. We propose an explainable verification procedure that attributes data ownership through re-generation, and further amplifies these fingerprints in the generative models through iterative data re-generation.
  arXiv  Detail & Related papers  (2024-02-23T10:48:21Z)
• A Dataset and Benchmark for Copyright Infringement Unlearning from Text-to-Image Diffusion Models [52.49582606341111]
  Copyright law confers creators the exclusive rights to reproduce, distribute, and monetize their creative works. Recent progress in text-to-image generation has introduced formidable challenges to copyright enforcement. We introduce a novel pipeline that harmonizes CLIP, ChatGPT, and diffusion models to curate a dataset.
  arXiv  Detail & Related papers  (2024-01-04T11:14:01Z)
• Learn to Unlearn for Deep Neural Networks: Minimizing Unlearning Interference with Gradient Projection [56.292071534857946]
  Recent data-privacy laws have sparked interest in machine unlearning. Challenge is to discard information about the forget'' data without altering knowledge about remaining dataset. We adopt a projected-gradient based learning method, named as Projected-Gradient Unlearning (PGU) We provide empirically evidence to demonstrate that our unlearning method can produce models that behave similar to models retrained from scratch across various metrics even when the training dataset is no longer accessible.
  arXiv  Detail & Related papers  (2023-12-07T07:17:24Z)
• Unlearn What You Want to Forget: Efficient Unlearning for LLMs [92.51670143929056]
  Large language models (LLMs) have achieved significant progress from pre-training on and memorizing a wide range of textual data. This process might suffer from privacy issues and violations of data protection regulations. We propose an efficient unlearning framework that could efficiently update LLMs without having to retrain the whole model after data removals.
  arXiv  Detail & Related papers  (2023-10-31T03:35:59Z)
• Your Room is not Private: Gradient Inversion Attack on Reinforcement Learning [47.96266341738642]
  Privacy emerges as a pivotal concern within the realm of embodied AI, as the robot accesses substantial personal information. This paper proposes an attack on the value-based algorithm and the gradient-based algorithm, utilizing gradient inversion to reconstruct states, actions, and supervision signals.
  arXiv  Detail & Related papers  (2023-06-15T16:53:26Z)
• A Survey of Machine Unlearning [56.017968863854186]
  Recent regulations now require that, on request, private information about a user must be removed from computer systems. ML models often remember' the old data. Recent works on machine unlearning have not been able to completely solve the problem.
  arXiv  Detail & Related papers  (2022-09-06T08:51:53Z)
• Disentangling private classes through regularization [8.72305226979945]
  We propose DisP, an approach for deep learning models disentangling the information related to some classes we desire to keep private. DisP is a regularization strategy de-correlating the features belonging to the same private class at training time, hiding the information of private classes membership. Our experiments on state-of-the-art deep learning models show the effectiveness of DisP.
  arXiv  Detail & Related papers  (2022-07-05T12:35:47Z)
• Model-Agnostic Multitask Fine-tuning for Few-shot Vision-Language Transfer Learning [59.38343286807997]
  We propose Model-Agnostic Multitask Fine-tuning (MAMF) for vision-language models on unseen tasks. Compared with model-agnostic meta-learning (MAML), MAMF discards the bi-level optimization and uses only first-order gradients. We show that MAMF consistently outperforms the classical fine-tuning method for few-shot transfer learning on five benchmark datasets.
  arXiv  Detail & Related papers  (2022-03-09T17:26:53Z)
• Representative & Fair Synthetic Data [68.8204255655161]
  We present a framework to incorporate fairness constraints into the self-supervised learning process. We generate a representative as well as fair version of the UCI Adult census data set. We consider representative & fair synthetic data a promising future building block to teach algorithms not on historic worlds, but rather on the worlds that we strive to live in.
  arXiv  Detail & Related papers  (2021-04-07T09:19:46Z)

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.