Towards Robust Knowledge Unlearning: An Adversarial Framework for Assessing and Improving Unlearning Robustness in Large Language Models

• URL: http://arxiv.org/abs/2408.10682v1
• Date: Tue, 20 Aug 2024 09:36:04 GMT
• Title: Towards Robust Knowledge Unlearning: An Adversarial Framework for Assessing and Improving Unlearning Robustness in Large Language Models
• Authors: Hongbang Yuan, Zhuoran Jin, Pengfei Cao, Yubo Chen, Kang Liu, Jun Zhao,
• Abstract summary: We design Dynamic Unlearning Attack (DUA), a dynamic and automated framework to attack unlearned models. We propose Latent Adrial Unlearning (LAU), a universal framework that effectively enhances the robustness of the unlearned process. We demonstrate that LAU improves unlearning effectiveness by over $53.5%$, cause only less than a $11.6%$ reduction in neighboring knowledge, and have almost no impact on the model's general capabilities.
• Score: 19.015202590038996
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: LLM have achieved success in many fields but still troubled by problematic content in the training corpora. LLM unlearning aims at reducing their influence and avoid undesirable behaviours. However, existing unlearning methods remain vulnerable to adversarial queries and the unlearned knowledge resurfaces after the manually designed attack queries. As part of a red-team effort to proactively assess the vulnerabilities of unlearned models, we design Dynamic Unlearning Attack (DUA), a dynamic and automated framework to attack these models and evaluate their robustness. It optimizes adversarial suffixes to reintroduce the unlearned knowledge in various scenarios. We find that unlearned knowledge can be recovered in $55.2\%$ of the questions, even without revealing the unlearned model's parameters. In response to this vulnerability, we propose Latent Adversarial Unlearning (LAU), a universal framework that effectively enhances the robustness of the unlearned process. It formulates the unlearning process as a min-max optimization problem and resolves it through two stages: an attack stage, where perturbation vectors are trained and added to the latent space of LLMs to recover the unlearned knowledge, and a defense stage, where previously trained perturbation vectors are used to enhance unlearned model's robustness. With our LAU framework, we obtain two robust unlearning methods, AdvGA and AdvNPO. We conduct extensive experiments across multiple unlearning benchmarks and various models, and demonstrate that they improve the unlearning effectiveness by over $53.5\%$, cause only less than a $11.6\%$ reduction in neighboring knowledge, and have almost no impact on the model's general capabilities.

Related papers

• When Machine Unlearning Meets Retrieval-Augmented Generation (RAG): Keep Secret or Forget Knowledge? [15.318301783084681]
  Large language models (LLMs) can inadvertently learn and retain sensitive information and harmful content during training. We propose a lightweight unlearning framework based on Retrieval-Augmented Generation (RAG) technology. We evaluate our framework through extensive experiments on both open-source and closed-source models, including ChatGPT, Gemini, Llama-2-7b-chat-hf, and PaLM 2.
  arXiv  Detail & Related papers  (2024-10-20T03:51:01Z)
• 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)
• LLMs-as-Instructors: Learning from Errors Toward Automating Model Improvement [93.38736019287224]
  "LLMs-as-Instructors" framework autonomously enhances the training of smaller target models. Inspired by the theory of "Learning from Errors", this framework employs an instructor LLM to meticulously analyze the specific errors within a target model. Within this framework, we implement two strategies: "Learning from Error," which focuses solely on incorrect responses to tailor training data, and "Learning from Error by Contrast", which uses contrastive learning to analyze both correct and incorrect responses for a deeper understanding of errors.
  arXiv  Detail & Related papers  (2024-06-29T17:16:04Z)
• UnUnlearning: Unlearning is not sufficient for content regulation in advanced generative AI [50.61495097098296]
  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.
  arXiv  Detail & Related papers  (2024-06-27T10:24:35Z)
• Unlearning with Control: Assessing Real-world Utility for Large Language Model Unlearning [97.2995389188179]
  Recent research has begun to approach large language models (LLMs) unlearning via gradient ascent (GA) Despite their simplicity and efficiency, we suggest that GA-based methods face the propensity towards excessive unlearning. We propose several controlling methods that can regulate the extent of excessive unlearning.
  arXiv  Detail & Related papers  (2024-06-13T14:41:00Z)
• Large Language Model Unlearning via Embedding-Corrupted Prompts [10.889859281637406]
  We present textbfEmbedding-COrrupted (ECO) Prompts, a lightweight unlearning framework for large language models. We enforce an unlearned state during inference by employing a prompt classifier to identify and safeguard prompts to forget. We find that these embedding-corrupted prompts not only lead to desirable outputs that satisfy the unlearning objective but also closely approximate the output from a model that has never been trained on the data intended for forgetting.
  arXiv  Detail & Related papers  (2024-06-12T06:56:20Z)
• 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)
• 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)
• 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)

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.