UnStar: Unlearning with Self-Taught Anti-Sample Reasoning for LLMs

• URL: http://arxiv.org/abs/2410.17050v1
• Date: Tue, 22 Oct 2024 14:30:03 GMT
• Title: UnStar: Unlearning with Self-Taught Anti-Sample Reasoning for LLMs
• Authors: Yash Sinha, Murari Mandal, Mohan Kankanhalli,
• Abstract summary: We introduce UnSTAR: Unlearning with Self-Taught Anti-Sample Reasoning for large language models (LLMs) Our contributions are threefold; first, we propose a novel concept of anti-sample-induced unlearning; second, we generate anti-samples by leveraging misleading rationales, which help reverse learned associations and accelerate the unlearning process. Results demonstrate that anti-samples offer an efficient, targeted unlearning strategy for LLMs, opening new avenues for privacy-preserving machine learning and model modification.
• Score: 10.335361310419826
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: The key components of machine learning are data samples for training, model for learning patterns, and loss function for optimizing accuracy. Analogously, unlearning can potentially be achieved through anti-data samples (or anti-samples), unlearning method, and reversed loss function. While prior research has explored unlearning methods and reversed loss functions, the potential of anti-samples remains largely untapped. In this paper, we introduce UnSTAR: Unlearning with Self-Taught Anti-Sample Reasoning for large language models (LLMs). Our contributions are threefold; first, we propose a novel concept of anti-sample-induced unlearning; second, we generate anti-samples by leveraging misleading rationales, which help reverse learned associations and accelerate the unlearning process; and third, we enable fine-grained targeted unlearning, allowing for the selective removal of specific associations without impacting related knowledge - something not achievable by previous works. Results demonstrate that anti-samples offer an efficient, targeted unlearning strategy for LLMs, opening new avenues for privacy-preserving machine learning and model modification.

Related papers

• Forgetting Similar Samples: Can Machine Unlearning Do it Better? [35.26900233614191]
  We argue that machine unlearning methods mainly aim at removing samples rather than removing samples' influence on the model.<n>We conduct a study to evaluate the effectiveness of existing unlearning schemes when the training dataset includes many samples similar to those targeted for unlearning.<n>Our experiments, conducted on four carefully constructed datasets with thorough analysis, reveal a notable gap between the expected and actual performance of most existing unlearning methods.
  arXiv  Detail & Related papers  (2026-01-11T14:55:57Z)
• Zero-Shot Machine Unlearning with Proxy Adversarial Data Generation [23.668928015009087]
  Machine unlearning aims to remove the influence of specific samples from a trained model.<n>Existing unlearning algorithms depend on the remaining data to prevent this issue.<n>This paper presents a novel framework, ZS-PAG, to fill this gap.
  arXiv  Detail & Related papers  (2025-07-29T12:16:55Z)
• Model Collapse Is Not a Bug but a Feature in Machine Unlearning for LLMs [54.167494079321465]
  Current unlearning methods for LLMs optimize on the private information they seek to remove by incorporating it into their fine-tuning data.<n>We propose a novel unlearning method-Partial Model Collapse (PMC), which does not require unlearning targets in the unlearning objective.
  arXiv  Detail & Related papers  (2025-07-06T03:08:49Z)
• FedMUA: Exploring the Vulnerabilities of Federated Learning to Malicious Unlearning Attacks [17.74292717846646]
  We introduce a novel malicious unlearning attack dubbed FedMUA. We show that FedMUA can induce misclassification on target samples and can achieve an 80% attack success rate.
  arXiv  Detail & Related papers  (2025-01-21T03:07:03Z)
• Attribute-to-Delete: Machine Unlearning via Datamodel Matching [65.13151619119782]
  Machine unlearning -- efficiently removing a small "forget set" training data on a pre-divertrained machine learning model -- has recently attracted interest. Recent research shows that machine unlearning techniques do not hold up in such a challenging setting.
  arXiv  Detail & Related papers  (2024-10-30T17:20:10Z)
• A Closer Look at Machine Unlearning for Large Language Models [46.245404272612795]
  Large language models (LLMs) may memorize sensitive or copyrighted content, raising privacy and legal concerns. We discuss several issues in machine unlearning for LLMs and provide our insights on possible approaches.
  arXiv  Detail & Related papers  (2024-10-10T16:56:05Z)
• 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)
• Learn What You Want to Unlearn: Unlearning Inversion Attacks against Machine Unlearning [16.809644622465086]
  We conduct the first investigation to understand the extent to which machine unlearning can leak the confidential content of unlearned data. Under the Machine Learning as a Service setting, we propose unlearning inversion attacks that can reveal the feature and label information of an unlearned sample. The experimental results indicate that the proposed attack can reveal the sensitive information of the unlearned data.
  arXiv  Detail & Related papers  (2024-04-04T06:37:46Z)
• Contrastive Unlearning: A Contrastive Approach to Machine Unlearning [30.38966646250252]
  We propose a contrastive unlearning framework, leveraging the concept of representation learning for more effective unlearning. We show that contrastive unlearning achieves the best unlearning effects and efficiency with the lowest performance loss compared with the state-of-the-art algorithms.
  arXiv  Detail & Related papers  (2024-01-19T02:16:30Z)
• 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)
• ReEval: Automatic Hallucination Evaluation for Retrieval-Augmented Large Language Models via Transferable Adversarial Attacks [91.55895047448249]
  This paper presents ReEval, an LLM-based framework using prompt chaining to perturb the original evidence for generating new test cases. We implement ReEval using ChatGPT and evaluate the resulting variants of two popular open-domain QA datasets. Our generated data is human-readable and useful to trigger hallucination in large language models.
  arXiv  Detail & Related papers  (2023-10-19T06:37:32Z)
• Combating Label Noise With A General Surrogate Model For Sample Selection [84.61367781175984]
  We propose to leverage the vision-language surrogate model CLIP to filter noisy samples automatically. We validate the effectiveness of our proposed method on both real-world and synthetic noisy datasets.
  arXiv  Detail & Related papers  (2023-10-16T14:43:27Z)
• Self-Supervised Dataset Distillation for Transfer Learning [77.4714995131992]
  We propose a novel problem of distilling an unlabeled dataset into a set of small synthetic samples for efficient self-supervised learning (SSL) We first prove that a gradient of synthetic samples with respect to a SSL objective in naive bilevel optimization is textitbiased due to randomness originating from data augmentations or masking. We empirically validate the effectiveness of our method on various applications involving transfer learning.
  arXiv  Detail & Related papers  (2023-10-10T10:48:52Z)
• Learn to Unlearn: A Survey on Machine Unlearning [29.077334665555316]
  This article presents a review of recent machine unlearning techniques, verification mechanisms, and potential attacks. We highlight emerging challenges and prospective research directions. We aim for this paper to provide valuable resources for integrating privacy, equity, andresilience into ML systems.
  arXiv  Detail & Related papers  (2023-05-12T14:28:02Z)
• Model Sparsity Can Simplify Machine Unlearning [33.18951938708467]
  In response to recent data regulation requirements, machine unlearning (MU) has emerged as a critical process. Our study introduces a novel model-based perspective: model sparsification via weight pruning. We show in both theory and practice that model sparsity can boost the multi-criteria unlearning performance of an approximate unlearner.
  arXiv  Detail & Related papers  (2023-04-11T02:12:02Z)
• Temporal Output Discrepancy for Loss Estimation-based Active Learning [65.93767110342502]
  We present a novel deep active learning approach that queries the oracle for data annotation when the unlabeled sample is believed to incorporate high loss. Our approach achieves superior performances than the state-of-the-art active learning methods on image classification and semantic segmentation tasks.
  arXiv  Detail & Related papers  (2022-12-20T19:29:37Z)

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.