LLM Unlearning for Cyber Defense: A Survey on Methods, Challenges, and Emerging Threats

• URL: http://arxiv.org/abs/2607.16227v1
• Date: Tue, 23 Jun 2026 00:17:34 GMT
• Title: LLM Unlearning for Cyber Defense: A Survey on Methods, Challenges, and Emerging Threats
• Abstract summary: LLMs are increasingly deployed in security-critical systems across healthcare, finance, education, and decision support.<n>Their inability to forget creates serious cybersecurity, privacy, and safety risks.<n>This survey examines LLM unlearning through the lens of security, robustness, and verifiable forgetting.
• Score: 0.7799351572681111
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: LLMs are increasingly deployed in security-critical systems across healthcare, finance, education, and decision support, yet their inability to forget creates serious cybersecurity, privacy, and safety risks. Sensitive personal information, copyrighted material, hazardous domain knowledge, and memorized training data remain encoded across billions of parameters long after deployment, leaving models vulnerable to extraction, jailbreak attacks, membership inference, and regulatory non-compliance. Real-world incidents, from chatbots regenerating private information to fabricated legal citations producing direct legal and financial cost, place the problem at the center of the emerging-threats landscape rather than the realm of speculation. Because retraining billion-parameter models on revised corpora is computationally infeasible, and because knowledge within an LLM is distributed and entangled across parameters rather than localized to identifiable units, LLM unlearning has emerged as the principal cyber defense response, aiming to remove or suppress targeted knowledge from a trained model without retraining and without eroding what the model should still know. A central question, however, remains unresolved. Do current methods genuinely remove knowledge, or do they only stop the model from expressing it under ordinary prompting conditions? This survey examines LLM unlearning through the lens of security, robustness, and verifiable forgetting, with primary focus on gradient-based methods, which have come to dominate the field due to their compatibility with existing training pipelines and their scalability to billion-parameter models.

Related papers

• KUDA: Knowledge Unlearning by Deviating Representation for Large Language Models [26.418820118903852]
  Large language models (LLMs) acquire a large amount of knowledge through pre-training on vast and diverse corpora.<n>LLMs unlearning is a promising technique to reduce risks associated with sensitive, copyrighted, or harmful content in training data.<n>We propose Knowledge Unlearning by Deviating representAtion (KUDA) to achieve effective unlearning at the knowledge level of LLMs.
  arXiv  Detail & Related papers  (2026-02-22T17:16:49Z)
• Forgetting-MarI: LLM Unlearning via Marginal Information Regularization [6.979586479353831]
  Existing unlearning methods often degrade model performance by removing more information than necessary when attempting to ''forget'' specific data.<n>We introduce Forgetting-MarI, an LLM unlearning framework that provably removes only the additional (marginal) information contributed by the data to be unlearned.<n>By penalizing marginal information, our method yields an explicit upper bound on the unlearn dataset's residual influence in the trained models, providing provable undetectability.
  arXiv  Detail & Related papers  (2025-11-14T22:48:39Z)
• Unlearning Imperative: Securing Trustworthy and Responsible LLMs through Engineered Forgetting [0.0]
  Large language models in sensitive domains can't ensure that private information can be permanently forgotten.<n>Retraining from the beginning is prohibitively costly.<n>Existing unlearning methods remain fragmented, difficult to verify, and often vulnerable to recovery.
  arXiv  Detail & Related papers  (2025-11-13T01:29:05Z)
• A Survey on Unlearning in Large Language Models [18.262778815699345]
  Large Language Models (LLMs) have revolutionized natural language processing, yet their training on massive corpora poses significant risks.<n>To mitigate these issues and align with legal and ethical standards such as the "right to be forgotten", machine unlearning has emerged as a critical technique.<n>This survey provides a systematic review of over 180 papers on LLM unlearning published since 2021, focusing exclusively on large-scale generative models.
  arXiv  Detail & Related papers  (2025-10-29T02:34:17Z)
• A Survey on Data Security in Large Language Models [12.23432845300652]
  Large Language Models (LLMs) are a foundation in advancing natural language processing, power applications such as text generation, machine translation, and conversational systems.<n>Despite their transformative potential, these models inherently rely on massive amounts of training data, often collected from diverse and uncurated sources, which exposes them to serious data security risks.<n>Harmful or malicious data can compromise model behavior, leading to issues such as toxic output, hallucinations, and vulnerabilities to threats such as prompt injection or data poisoning.<n>This survey offers a comprehensive overview of the main data security risks facing LLMs and reviews current defense strategies, including adversarial
  arXiv  Detail & Related papers  (2025-08-04T11:28:34Z)
• Security Concerns for Large Language Models: A Survey [4.1824815480811806]
  Large Language Models (LLMs) have caused a revolution in natural language processing, but their capabilities also introduce new security vulnerabilities.<n>This survey provides a comprehensive overview of these emerging concerns, categorizing threats into several key areas.<n>We conclude by emphasizing the importance of advancing robust, multi-layered security strategies to ensure LLMs are safe and beneficial.
  arXiv  Detail & Related papers  (2025-05-24T22:22:43Z)
• Purple-teaming LLMs with Adversarial Defender Training [57.535241000787416]
  We present Purple-teaming LLMs with Adversarial Defender training (PAD) PAD is a pipeline designed to safeguard LLMs by novelly incorporating the red-teaming (attack) and blue-teaming (safety training) techniques. PAD significantly outperforms existing baselines in both finding effective attacks and establishing a robust safe guardrail.
  arXiv  Detail & Related papers  (2024-07-01T23:25:30Z)
• Offset Unlearning for Large Language Models [49.851093293780615]
  delta-Unlearning is an offset unlearning framework for black-box LLMs.<n>We show that delta-Unlearning can effectively unlearn target data while maintaining similar or even stronger performance on general out-of-forget-scope tasks.
  arXiv  Detail & Related papers  (2024-04-17T03:39:51Z)
• Unveiling the Misuse Potential of Base Large Language Models via In-Context Learning [61.2224355547598]
  Open-sourcing of large language models (LLMs) accelerates application development, innovation, and scientific progress. Our investigation exposes a critical oversight in this belief. By deploying carefully designed demonstrations, our research demonstrates that base LLMs could effectively interpret and execute malicious instructions.
  arXiv  Detail & Related papers  (2024-04-16T13:22:54Z)
• 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)
• The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearning [87.1610740406279]
  White House Executive Order on Artificial Intelligence highlights the risks of large language models (LLMs) empowering malicious actors in developing biological, cyber, and chemical weapons. Current evaluations are private, preventing further research into mitigating risk. We publicly release the Weapons of Mass Destruction Proxy benchmark, a dataset of 3,668 multiple-choice questions.
  arXiv  Detail & Related papers  (2024-03-05T18:59:35Z)
• Rethinking Machine Unlearning for Large Language Models [85.92660644100582]
  We explore machine unlearning in the domain of large language models (LLMs)<n>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)

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.