Towards Label-Only Membership Inference Attack against Pre-trained Large Language Models

• URL: http://arxiv.org/abs/2502.18943v1
• Date: Wed, 26 Feb 2025 08:47:19 GMT
• Title: Towards Label-Only Membership Inference Attack against Pre-trained Large Language Models
• Authors: Yu He, Boheng Li, Liu Liu, Zhongjie Ba, Wei Dong, Yiming Li, Zhan Qin, Kui Ren, Chun Chen,
• Abstract summary: Membership Inference Attacks (MIAs) aim to predict whether a data sample belongs to the model's training set or not.<n>We propose textbfPETAL: a label-only membership inference attack based on textbfPEr-textbfToken semtextbfAntic simitextbfLL.
• Score: 34.39913818362284
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Membership Inference Attacks (MIAs) aim to predict whether a data sample belongs to the model's training set or not. Although prior research has extensively explored MIAs in Large Language Models (LLMs), they typically require accessing to complete output logits (\ie, \textit{logits-based attacks}), which are usually not available in practice. In this paper, we study the vulnerability of pre-trained LLMs to MIAs in the \textit{label-only setting}, where the adversary can only access generated tokens (text). We first reveal that existing label-only MIAs have minor effects in attacking pre-trained LLMs, although they are highly effective in inferring fine-tuning datasets used for personalized LLMs. We find that their failure stems from two main reasons, including better generalization and overly coarse perturbation. Specifically, due to the extensive pre-training corpora and exposing each sample only a few times, LLMs exhibit minimal robustness differences between members and non-members. This makes token-level perturbations too coarse to capture such differences. To alleviate these problems, we propose \textbf{PETAL}: a label-only membership inference attack based on \textbf{PE}r-\textbf{T}oken sem\textbf{A}ntic simi\textbf{L}arity. Specifically, PETAL leverages token-level semantic similarity to approximate output probabilities and subsequently calculate the perplexity. It finally exposes membership based on the common assumption that members are `better' memorized and have smaller perplexity. We conduct extensive experiments on the WikiMIA benchmark and the more challenging MIMIR benchmark. Empirically, our PETAL performs better than the extensions of existing label-only attacks against personalized LLMs and even on par with other advanced logit-based attacks across all metrics on five prevalent open-source LLMs.

Related papers

• Tag&Tab: Pretraining Data Detection in Large Language Models Using Keyword-Based Membership Inference Attack [26.083244046813512]
  Large language models (LLMs) have become essential digital task assistance tools. Recent studies on the detection of pretraining data in LLMs have primarily focused on sentence-level or paragraph-level membership inference attacks. We propose Tag&Tab, a novel approach for detecting data that has been used as part of the LLM pretraining.
  arXiv  Detail & Related papers  (2025-01-14T21:55:37Z)
• Not all tokens are created equal: Perplexity Attention Weighted Networks for AI generated text detection [49.15148871877941]
  Next-token distribution outputs offer a theoretically appealing approach for detection of large language models (LLMs)<n>We propose the Perplexity Attention Weighted Network (PAWN), which uses the last hidden states of the LLM and positions to weight the sum of a series of features based on metrics from the next-token distribution across the sequence length.<n>PAWN shows competitive and even better performance in-distribution than the strongest baselines with a fraction of their trainable parameters.
  arXiv  Detail & Related papers  (2025-01-07T17:00:49Z)
• 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. EM-MIA achieves state-of-the-art results on WikiMIA.
  arXiv  Detail & Related papers  (2024-10-10T03:31:16Z)
• SoK: Membership Inference Attacks on LLMs are Rushing Nowhere (and How to Fix It) [16.673210422615348]
  More than 10 new methods have been proposed to perform Membership Inference Attacks (MIAs) against LLMs. Contrary to traditional MIAs which rely on fixed-but randomized-records or models, these methods are mostly trained and tested on datasets collected post-hoc. This lack of randomization raises concerns of a distribution shift between members and non-members.
  arXiv  Detail & Related papers  (2024-06-25T23:12:07Z)
• ReCaLL: Membership Inference via Relative Conditional Log-Likelihoods [56.073335779595475]
  We propose ReCaLL (Relative Conditional Log-Likelihood), a novel membership inference attack (MIA) ReCaLL examines the relative change in conditional log-likelihoods when prefixing target data points with non-member context. 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)
• Alpaca against Vicuna: Using LLMs to Uncover Memorization of LLMs [61.04246774006429]
  We introduce a black-box prompt optimization method that uses an attacker LLM agent to uncover higher levels of memorization in a victim agent.<n>We observe that our instruction-based prompts generate outputs with 23.7% higher overlap with training data compared to the baseline prefix-suffix measurements.<n>Our findings show that instruction-tuned models can expose pre-training data as much as their base-models, if not more so, and using instructions proposed by other LLMs can open a new avenue of automated attacks.
  arXiv  Detail & Related papers  (2024-03-05T19:32:01Z)
• Do Membership Inference Attacks Work on Large Language Models? [141.2019867466968]
  Membership inference attacks (MIAs) attempt to predict whether a particular datapoint is a member of a target model's training data. We perform a large-scale evaluation of MIAs over a suite of language models trained on the Pile, ranging from 160M to 12B parameters. We find that MIAs barely outperform random guessing for most settings across varying LLM sizes and domains.
  arXiv  Detail & Related papers  (2024-02-12T17:52:05Z)
• Practical Membership Inference Attacks against Fine-tuned Large Language Models via Self-prompt Calibration [32.15773300068426]
  Membership Inference Attacks aim to infer whether a target data record has been utilized for model training. We propose a Membership Inference Attack based on Self-calibrated Probabilistic Variation (SPV-MIA)
  arXiv  Detail & Related papers  (2023-11-10T13:55:05Z)
• SeqXGPT: Sentence-Level AI-Generated Text Detection [62.3792779440284]
  We introduce a sentence-level detection challenge by synthesizing documents polished with large language models (LLMs) We then propose textbfSequence textbfX (Check) textbfGPT, a novel method that utilizes log probability lists from white-box LLMs as features for sentence-level AIGT detection.
  arXiv  Detail & Related papers  (2023-10-13T07:18:53Z)

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.