UnUnlearning: Unlearning is not sufficient for content regulation in advanced generative AI

• URL: http://arxiv.org/abs/2407.00106v1
• Date: Thu, 27 Jun 2024 10:24:35 GMT
• Title: UnUnlearning: Unlearning is not sufficient for content regulation in advanced generative AI
• Authors: Ilia Shumailov, Jamie Hayes, Eleni Triantafillou, Guillermo Ortiz-Jimenez, Nicolas Papernot, Matthew Jagielski, Itay Yona, Heidi Howard, Eugene Bagdasaryan,
• Abstract summary: We revisit the paradigm in which unlearning is used for Large Language Models (LLMs) We introduce a concept of ununlearning, where unlearned knowledge gets reintroduced in-context. We argue that content filtering for impermissible knowledge will be required and even exact unlearning schemes are not enough for effective content regulation.
• Score: 50.61495097098296
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Exact unlearning was first introduced as a privacy mechanism that allowed a user to retract their data from machine learning models on request. Shortly after, inexact schemes were proposed to mitigate the impractical costs associated with exact unlearning. More recently unlearning is often discussed as an approach for removal of impermissible knowledge i.e. knowledge that the model should not possess such as unlicensed copyrighted, inaccurate, or malicious information. The promise is that if the model does not have a certain malicious capability, then it cannot be used for the associated malicious purpose. In this paper we revisit the paradigm in which unlearning is used for in Large Language Models (LLMs) and highlight an underlying inconsistency arising from in-context learning. Unlearning can be an effective control mechanism for the training phase, yet it does not prevent the model from performing an impermissible act during inference. We introduce a concept of ununlearning, where unlearned knowledge gets reintroduced in-context, effectively rendering the model capable of behaving as if it knows the forgotten knowledge. As a result, we argue that content filtering for impermissible knowledge will be required and even exact unlearning schemes are not enough for effective content regulation. We discuss feasibility of ununlearning for modern LLMs and examine broader implications.

Related papers

• 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)
• To Forget or Not? Towards Practical Knowledge Unlearning for Large Language Models [39.39428450239399]
  Large Language Models (LLMs) trained on extensive corpora inevitably retain sensitive data, such as personal privacy information and copyrighted material. Recent advancements in knowledge unlearning involve updating LLM parameters to erase specific knowledge. We introduce KnowUnDo to evaluate if the unlearning process inadvertently erases essential knowledge.
  arXiv  Detail & Related papers  (2024-07-02T03:34:16Z)
• Textual Unlearning Gives a False Sense of Unlearning [12.792770622915906]
  Language models (LMs) are susceptible to "memorizing" training data, including a large amount of private or copyright-protected content. We propose the Textual Unlearning Leakage Attack (TULA), where an adversary can infer information about unlearned data only by accessing the models before and after unlearning. Our work is the first to reveal that machine unlearning in LMs can inversely create greater knowledge risks and inspire the development of more secure unlearning mechanisms.
  arXiv  Detail & Related papers  (2024-06-19T08:51:54Z)
• Rethinking Machine Unlearning for Large Language Models [85.92660644100582]
  We explore machine unlearning in the domain of large language models (LLMs) This initiative aims to eliminate undesirable data influence (e.g., sensitive or illegal information) and the associated model capabilities.
  arXiv  Detail & Related papers  (2024-02-13T20:51:58Z)
• TOFU: A Task of Fictitious Unlearning for LLMs [99.92305790945507]
  Large language models trained on massive corpora of data from the web can reproduce sensitive or private data raising both legal and ethical concerns. Unlearning, or tuning models to forget information present in their training data, provides us with a way to protect private data after training. We present TOFU, a benchmark aimed at helping deepen our understanding of unlearning.
  arXiv  Detail & Related papers  (2024-01-11T18:57:12Z)
• A Duty to Forget, a Right to be Assured? Exposing Vulnerabilities in Machine Unlearning Services [31.347825826778276]
  We try to explore the potential threats posed by unlearning services in Machine Learning (ML) We propose two strategies that leverage over-unlearning to measure the impact on the trade-off balancing. Results indicate significant potential for both strategies to undermine model efficacy in unlearning scenarios.
  arXiv  Detail & Related papers  (2023-09-15T08:00:45Z)
• On the Necessity of Auditable Algorithmic Definitions for Machine Unlearning [13.149070833843133]
  Machine unlearning, i.e. having a model forget about some of its training data, has become increasingly important as privacy legislation promotes variants of the right-to-be-forgotten. We first show that the definition that underlies approximate unlearning, which seeks to prove the approximately unlearned model is close to an exactly retrained model, is incorrect because one can obtain the same model using different datasets. We then turn to exact unlearning approaches and ask how to verify their claims of unlearning.
  arXiv  Detail & Related papers  (2021-10-22T16:16:56Z)
• Machine Unlearning of Features and Labels [72.81914952849334]
  We propose first scenarios for unlearning and labels in machine learning models. Our approach builds on the concept of influence functions and realizes unlearning through closed-form updates of model parameters.
  arXiv  Detail & Related papers  (2021-08-26T04:42:24Z)

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.