mlsanityData to 14 Oct 2026

Harry Potter is Still Here! Probing Knowledge Leakage in Targeted Unlearned Large Language Models via Automated Adversarial Prompting

arXiv 2505.17160 ↗First posted 22 May 2025cs.CL cs.AI cs.CRcited by 7

On the map: LLM safety and security → Machine unlearning

Abstract (arXiv)

This work presents LURK (Latent UnleaRned Knowledge), a novel framework that probes for hidden retained knowledge in unlearned LLMs through adversarial suffix prompting. LURK automatically generates adversarial prompt suffixes designed to elicit residual knowledge about the Harry Potter domain, a commonly used benchmark for unlearning. Our experiments reveal that even models deemed successfully unlearned can leak idiosyncratic information under targeted adversarial conditions, highlighting critical limitations of current unlearning evaluation standards. By uncovering latent knowledge through indirect probing, LURK offers a more rigorous and diagnostic tool for assessing the robustness of unlearning algorithms. All code will be publicly available.

Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). Placed in Machine unlearning, one of 12 directions in LLM safety and security. Builds on 16 of its 22 references that are in the map. First posted on arXiv 22 May 2025.

Builds on

16 of 22 references.

Closest ancestors · 8

Same direction, newest first

  1. 2024LLM Unlearning via Loss Adjustment with Only Forget Data14 Oct
  2. 2024MUSE: Machine Unlearning Six-Way Evaluation for Language Models8 Jul
  3. 2024Large Language Model Unlearning via Embedding-Corrupted Prompts12 Jun
  4. 2024Rethinking LLM Memorization through the Lens of Adversarial Compression23 Apr
  5. 2024Negative Preference Optimization: From Catastrophic Collapse to Effective Unlearning8 Apr
  6. 2024TOFU: A Task of Fictitious Unlearning for LLMs11 Jan
  7. 2023Who's Harry Potter? Approximate Unlearning in LLMs3 Oct
  8. 2022Knowledge Unlearning for Mitigating Privacy Risks in Language Models4 Oct

Other references · 8

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 13,028
  3. 2022OPT: Open Pre-trained Transformer Language Modelscited by 3,512
  4. 2023Universal and Transferable Adversarial Attacks on Aligned Language Modelscited by 3,104
  5. 2023Catastrophic Jailbreak of Open-source LLMs via Exploiting Generationcited by 451
  6. 2023MasterKey: Automated Jailbreak Across Multiple Large Language Model Chatbotscited by 183
  7. 2024Soft Prompt Threats: Attacking Safety Alignment and Unlearning in Open-Source LLMs through the Embedding Spacecited by 91
  8. 2023In-context Pretraining: Language Modeling Beyond Document Boundariescited by 79

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 3; 2026: 4.

7 papers.

  1. 2025SoK: Machine Unlearning for Large Language Modelscited by 11
  2. 2026STaR: Sensitive Trajectory Regulation for Unlearning in Large Reasoning Modelscited by 2
  3. 2025What the "Spotless" Mind Remembers: How Knowledge Entanglement Shapes What Leaks After Unlearning in LLMscited by 1
  4. 2026A Comprehensive Evaluation of LLM Unlearning Robustness under Multi-Turn Interactioncited by 1
  5. 2025Randomized Masked Finetuning: An Efficient Way to Mitigate Memorization of PIIs in LLMscited by 0
  6. 2026Extracting Forgotten Prompts from Targeted Unlearned Modelscited by 0
  7. 2026RA2: Retain-Anchored Attraction Preserves Forget-Adjacent Utility in LLM Unlearningcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Towards Robust Knowledge Unlearning: An Adversarial Framework for Assessing and Improving Unlearning Robustness in Large Language Models
  2. 2026From Domains to Instances: Dual-Granularity Data Synthesis for LLM Unlearning
  3. 2025Erase or Hide? Suppressing Spurious Unlearning Neurons for Robust Unlearning
  4. 2025Keeping an Eye on LLM Unlearning: The Hidden Risk and Remedy
  5. 2024Unlearning or Obfuscating? Jogging the Memory of Unlearned LLMs via Benign Relearning
  6. 2025Improving LLM Unlearning Robustness via Random Perturbations
  7. 2026Unlearning in LLMs: Methods, Evaluation, and Open Challenges
  8. 2025Prompt Attacks Reveal Superficial Knowledge Removal in Unlearning Methods