Identifying Unlearned Data in LLMs via Membership Inference Attacks (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing work evaluates approximate unlearning under a retrieval paradigm, where adversaries attempt to extract residual knowledge given partial information of the unlearning target. |
| Approach: | They propose a framework to evaluate unlearning membership attacks using member inference techniques to exploit the forget set. |
| Outcome: | The proposed framework assesses whether unlearning leaves behind detectable artifacts that can be exploited to infer membership in the forget set. |
Similar Papers
Neural Breadcrumbs: Membership Inference Attacks on LLMs Through Hidden State and Attention Pattern Analysis (2026.eacl-long)
Copied to clipboard
| Challenge: | Membership inference attacks (MIAs) reveal whether specific data was used to train machine learning models, serving as important tools for privacy auditing and compliance assessment. |
| Approach: | They propose to examine LLMs’ internal representations rather than just their outputs to gain additional insights into potential membership inference signals. |
| Outcome: | The proposed framework yields strong membership detection across several model families achieving average AUC scores of 0.85 on popular MIA benchmarks. |
Tokens for Learning, Tokens for Unlearning: Mitigating Membership Inference Attacks in Large Language Models via Dual-Purpose Training (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing defenses for large language models do not account for the sequential nature of text data. |
| Approach: | They propose a lightweight yet effective empirical privacy defense that leverages token-specific characteristics to protect training data of large language models. |
| Outcome: | The proposed approach provides strong protection against membership inference attacks and improves language modeling performance by 10% across different LLM architectures and datasets compared to baselines. |
R.R.: Unveiling LLM Training Privacy through Recollection and Ranking (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing privacy attacks focus on membership inference or data extraction, but reconstructing specific personally identifiable information (PII) in training data remains challenging. |
| Approach: | They propose a two-step privacy stealing attack that enables attackers to reconstruct PII entities from scrubbed training data where the PI I entities have been masked. |
| Outcome: | The proposed attack can reconstruct PII entities from scrubbed training data where the PI I entities have been masked. |
Unlearn What You Want to Forget: Efficient Unlearning for LLMs (2023.emnlp-main)
Copied to clipboard
| Challenge: | Large language models (LLMs) can be used to memorize a vast amount of data, but can suffer from privacy issues and data protection violations. |
| Approach: | They propose an efficient unlearning framework that could update LLMs without retraining them . they introduce lightweight unlearning layers learned with a selective teacher-student objective into transformers . |
| Outcome: | The proposed framework could update LLMs without having to retrain the whole model after data removals. |
CheckMIABench: Firm Foundations For Membership Inference Attacks on Language Models (2026.acl-short)
Copied to clipboard
| Challenge: | Membership inference attacks are a canonical way to assess a machine learning model’s privacy properties. |
| Approach: | They propose a framework for principled evaluation of membership inference attacks against large language models by leveraging the insight that training data before and after a fixed point during training are drawn from the same distribution. |
| Outcome: | The proposed framework can be used to evaluate membership inference attacks against large language models. |
Quantifying Privacy Risks of Masked Language Models Using Membership Inference Attacks (2022.emnlp-main)
Copied to clipboard
| Challenge: | Prior attempts at measuring leakage of MLMs via membership inference attacks have been inconclusive, implying potential robustness of Mlms to privacy attacks. |
| Approach: | They propose a stronger membership inference attack based on likelihood ratio hypothesis testing that involves an additional MLM to more accurately quantify the privacy risks of memorization in MLMs. |
| Outcome: | The proposed attack improves the AUC of prior membership inference attacks from 0.66 to an alarmingly high 0.90 level on models trained on medical notes. |
Robust Membership Inference for Large Language Models under Adversarial Generative Corruption (2026.acl-long)
Copied to clipboard
Yuanhong Huang, Huili Wang, Xueying Bai, Jinrui Wang, Jiajun Liu, Ziqin Wang, Wanchun Ni, Shangguang Wang, Tao Qi
| Challenge: | Membership inference attacks are a promising tool for auditing training data of LLMs . existing methods rely on the assumption that LLM's assign higher confidence scores to training samples than to non-training ones. |
| Approach: | They propose a membership inference framework that can be robust against adversarial MIAs. |
| Outcome: | The proposed framework can be robust against adversarial MIA methods and AIGT detectors while maintaining the performance of baselines. |
Knowledge Unlearning for Mitigating Privacy Risks in Language Models (2023.acl-long)
Copied to clipboard
| Challenge: | Recent work shows that an adversary can extract training data from Pretrained Language Models including Personally Identifiable Information (PII) such as names, phone numbers, and email addresses. |
| Approach: | They propose to use knowledge unlearning to reduce privacy risks for LMs by performing gradient ascent on target token sequences instead of trying to unlearn all the data at once. |
| Outcome: | The proposed method can give a stronger empirical privacy guarantee in scenarios where the data vulnerable to extraction attacks are known a priori while being much more efficient and robust. |
Which Retain Set Matters for LLM Unlearning? A Case Study on Entity Unlearning (2025.findings-acl)
Copied to clipboard
| Challenge: | Large language models (LLMs) are prone to retaining unauthorized or sensitive information from their training data, which raises privacy concerns. |
| Approach: | They propose to use a group of queries that share similar syntactic structures with the data targeted for removal to investigate the effects of unlearning on various subsets of the retain set. |
| Outcome: | The proposed method reduces the retention set, the portion of training data that is not targeted for removal, and improves model performance across subsets. |
Preserving Privacy Through Dememorization: An Unlearning Technique For Mitigating Memorization Risks In Language Models (2023.emnlp-main)
Copied to clipboard
| Challenge: | Large Language models (LLMs) are trained on vast amounts of data, including sensitive information that poses a risk to personal privacy if exposed. |
| Approach: | They propose a novel unlearning approach that utilizes an efficient reinforcement learning feedback loop via proximal policy optimization to incentivize the LLMs to learn a paraphrasing policy to unlearn the pre-training data. |
| Outcome: | The proposed approach surpasses strong baselines and state-of-the-art methods in terms of its ability to generalize and strike a balance between privacy and LLM performance. |