(Token-Level) InfoRMIA: Stronger Membership Inference and Memorization Assessment for LLMs

• URL: http://arxiv.org/abs/2510.05582v2
• Date: Thu, 09 Oct 2025 10:03:33 GMT
• Title: (Token-Level) InfoRMIA: Stronger Membership Inference and Memorization Assessment for LLMs
• Authors: Jiashu Tao, Reza Shokri,
• Abstract summary: Large language models (LLMs) are now trained on nearly all available data, which amplifies the magnitude of information leakage.<n>Standard method to quantify privacy is via membership inference attacks.<n>We present InfoRMIA, a principled information-theoretic formulation of membership inference.
• Score: 13.601386341584545
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Machine learning models are known to leak sensitive information, as they inevitably memorize (parts of) their training data. More alarmingly, large language models (LLMs) are now trained on nearly all available data, which amplifies the magnitude of information leakage and raises serious privacy risks. Hence, it is more crucial than ever to quantify privacy risk before the release of LLMs. The standard method to quantify privacy is via membership inference attacks, where the state-of-the-art approach is the Robust Membership Inference Attack (RMIA). In this paper, we present InfoRMIA, a principled information-theoretic formulation of membership inference. Our method consistently outperforms RMIA across benchmarks while also offering improved computational efficiency. In the second part of the paper, we identify the limitations of treating sequence-level membership inference as the gold standard for measuring leakage. We propose a new perspective for studying membership and memorization in LLMs: token-level signals and analyses. We show that a simple token-based InfoRMIA can pinpoint which tokens are memorized within generated outputs, thereby localizing leakage from the sequence level down to individual tokens, while achieving stronger sequence-level inference power on LLMs. This new scope rethinks privacy in LLMs and can lead to more targeted mitigation, such as exact unlearning.

Related papers

• What Hard Tokens Reveal: Exploiting Low-confidence Tokens for Membership Inference Attacks against Large Language Models [2.621142288968429]
  Membership Inference Attacks (MIAs) attempt to determine whether a specific data sample was included in a model training/fine-tuning dataset.<n>We propose a novel membership inference approach that captures the token-level probabilities for low-confidence (hard) tokens.<n>Experiments on both domain-specific medical datasets and general-purpose benchmarks demonstrate that HT-MIA consistently outperforms seven state-of-the-art MIA baselines.
  arXiv  Detail & Related papers  (2026-01-27T22:31:10Z)
• AttenMIA: LLM Membership Inference Attack through Attention Signals [8.170623979629953]
  We introduce AttenMIA, a new MIA framework that exploits self-attention patterns inside the transformer model to infer membership.<n>We show that attention-based features consistently outperform baselines, particularly under the important low-false-positive metric.<n>We also show that using AttenMIA to replace other membership inference attacks in a data extraction framework results in training data extraction attacks that outperform the state of the art.
  arXiv  Detail & Related papers  (2026-01-26T03:45:56Z)
• PerProb: Indirectly Evaluating Memorization in Large Language Models [13.905375956316632]
  We propose PerProb, a label-free framework for indirectly assessing LLM vulnerabilities.<n>PerProb evaluates changes in perplexity and average log probability between data generated by victim and adversary models.<n>We evaluate PerProb's effectiveness across five datasets, revealing varying memory behaviors and privacy risks.
  arXiv  Detail & Related papers  (2025-12-16T17:10:01Z)
• Retracing the Past: LLMs Emit Training Data When They Get Lost [18.852558767604823]
  memorization of training data in large language models poses significant privacy and copyright concerns.<n>This paper introduces Confusion-Inducing Attacks (CIA), a principled framework for extracting memorized data.
  arXiv  Detail & Related papers  (2025-10-27T03:48:24Z)
• Scrub It Out! Erasing Sensitive Memorization in Code Language Models via Machine Unlearning [50.45435841411193]
  Code Language Models (CLMs) exhibit unintended memorization of sensitive training data, enabling verbatim reproduction of confidential information when specifically prompted.<n>We introduce CodeEraser, an advanced variant that selectively unlearns sensitive memorized segments in code while preserving the structural integrity and functional correctness of the surrounding code.
  arXiv  Detail & Related papers  (2025-09-17T07:12:35Z)
• Aligning Large Language Models to Follow Instructions and Hallucinate Less via Effective Data Filtering [66.5524727179286]
  NOVA is a framework designed to identify high-quality data that aligns well with the learned knowledge to reduce hallucinations.<n>It includes Internal Consistency Probing (ICP) and Semantic Equivalence Identification (SEI) to measure how familiar the LLM is with instruction data.<n>To ensure the quality of selected samples, we introduce an expert-aligned reward model, considering characteristics beyond just familiarity.
  arXiv  Detail & Related papers  (2025-02-11T08:05:56Z)
• Decoding Secret Memorization in Code LLMs Through Token-Level Characterization [6.92858396995673]
  Code Large Language Models (LLMs) have demonstrated remarkable capabilities in generating, understanding, and manipulating programming code.<n>LLMs inadvertently lead to the memorization of sensitive information, posing severe privacy risks.<n>We present a novel approach to characterize real and fake secrets generated by Code LLMs based on token probabilities.
  arXiv  Detail & Related papers  (2024-10-11T14:39:24Z)
• Detecting Training Data of Large Language Models via Expectation Maximization [62.28028046993391]
  We introduce EM-MIA, a novel membership inference method that iteratively refines membership scores and prefix scores via an expectation-maximization algorithm.<n> EM-MIA achieves state-of-the-art results on WikiMIA.
  arXiv  Detail & Related papers  (2024-10-10T03:31:16Z)
• LLM-PBE: Assessing Data Privacy in Large Language Models [111.58198436835036]
  Large Language Models (LLMs) have become integral to numerous domains, significantly advancing applications in data management, mining, and analysis. Despite the critical nature of this issue, there has been no existing literature to offer a comprehensive assessment of data privacy risks in LLMs. Our paper introduces LLM-PBE, a toolkit crafted specifically for the systematic evaluation of data privacy risks in LLMs.
  arXiv  Detail & Related papers  (2024-08-23T01:37:29Z)
• ReCaLL: Membership Inference via Relative Conditional Log-Likelihoods [56.073335779595475]
  We propose ReCaLL (Relative Conditional Log-Likelihood) to detect pretraining data by leveraging conditional language modeling capabilities.<n>Our empirical findings show that conditioning member data on non-member prefixes induces a larger decrease in log-likelihood compared to non-member data.<n>We conduct comprehensive experiments and show that ReCaLL achieves state-of-the-art performance on the WikiMIA dataset.
  arXiv  Detail & Related papers  (2024-06-23T00:23:13Z)
• CLAMBER: A Benchmark of Identifying and Clarifying Ambiguous Information Needs in Large Language Models [60.59638232596912]
  We introduce CLAMBER, a benchmark for evaluating large language models (LLMs) Building upon the taxonomy, we construct 12K high-quality data to assess the strengths, weaknesses, and potential risks of various off-the-shelf LLMs. Our findings indicate the limited practical utility of current LLMs in identifying and clarifying ambiguous user queries.
  arXiv  Detail & Related papers  (2024-05-20T14:34:01Z)
• Mitigating Approximate Memorization in Language Models via Dissimilarity Learned Policy [0.0]
  Large Language models (LLMs) are trained on large amounts of data. LLMs showed to memorize parts of the training data and emit those data verbatim when an adversary prompts appropriately.
  arXiv  Detail & Related papers  (2023-05-02T15:53:28Z)

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.