ReCaLL: Membership Inference via Relative Conditional Log-Likelihoods

• URL: http://arxiv.org/abs/2406.15968v1
• Date: Sun, 23 Jun 2024 00:23:13 GMT
• Title: ReCaLL: Membership Inference via Relative Conditional Log-Likelihoods
• Authors: Roy Xie, Junlin Wang, Ruomin Huang, Minxing Zhang, Rong Ge, Jian Pei, Neil Zhenqiang Gong, Bhuwan Dhingra,
• Abstract summary: 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.
• Score: 56.073335779595475
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The rapid scaling of large language models (LLMs) has raised concerns about the transparency and fair use of the pretraining data used for training them. Detecting such content is challenging due to the scale of the data and limited exposure of each instance during training. We propose ReCaLL (Relative Conditional Log-Likelihood), a novel membership inference attack (MIA) to detect LLMs' pretraining data by leveraging their conditional language modeling capabilities. ReCaLL examines the relative change in conditional log-likelihoods when prefixing target data points with non-member context. Our empirical findings show that conditioning member data on non-member prefixes induces a larger decrease in log-likelihood compared to non-member data. We conduct comprehensive experiments and show that ReCaLL achieves state-of-the-art performance on the WikiMIA dataset, even with random and synthetic prefixes, and can be further improved using an ensemble approach. Moreover, we conduct an in-depth analysis of LLMs' behavior with different membership contexts, providing insights into how LLMs leverage membership information for effective inference at both the sequence and token level.

Related papers

• Self-Comparison for Dataset-Level Membership Inference in Large (Vision-)Language Models [73.94175015918059]
  We propose a dataset-level membership inference method based on Self-Comparison. Our method does not require access to ground-truth member data or non-member data in identical distribution.
  arXiv  Detail & Related papers  (2024-10-16T23:05:59Z)
• Fine-tuning can Help Detect Pretraining Data from Large Language Models [7.7209640786782385]
  Current methods differentiate members and non-members by designing scoring functions, like Perplexity and Min-k%. We introduce a novel and effective method termed Fine-tuned Score Deviation (FSD), which improves the performance of current scoring functions for pretraining data detection.
  arXiv  Detail & Related papers  (2024-10-09T15:36:42Z)
• Con-ReCall: Detecting Pre-training Data in LLMs via Contrastive Decoding [118.75567341513897]
  Existing methods typically analyze target text in isolation or solely with non-member contexts. We propose Con-ReCall, a novel approach that leverages the asymmetric distributional shifts induced by member and non-member contexts.
  arXiv  Detail & Related papers  (2024-09-05T09:10:38Z)
• Feature-Adaptive and Data-Scalable In-Context Learning [36.01997148676005]
  FADS-ICL is a feature-adaptive and data-scalable in-context learning framework. It can leverage task-adaptive features to promote inference on the downstream task. FADS-ICL consistently outperforms previous state-of-the-art methods.
  arXiv  Detail & Related papers  (2024-05-17T12:32:53Z)
• 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)
• Improving Input-label Mapping with Demonstration Replay for In-context Learning [67.57288926736923]
  In-context learning (ICL) is an emerging capability of large autoregressive language models. We propose a novel ICL method called Sliding Causal Attention (RdSca) We show that our method significantly improves the input-label mapping in ICL demonstrations.
  arXiv  Detail & Related papers  (2023-10-30T14:29:41Z)
• Explaining Emergent In-Context Learning as Kernel Regression [61.57151500616111]
  Large language models (LLMs) have initiated a paradigm shift in transfer learning. In this paper, we investigate the reason why a transformer-based language model can accomplish in-context learning after pre-training. We find that during ICL, the attention and hidden features in LLMs match the behaviors of a kernel regression.
  arXiv  Detail & Related papers  (2023-05-22T06:45:02Z)
• Semi-Leak: Membership Inference Attacks Against Semi-supervised Learning [42.089020844936805]
  Semi-supervised learning (SSL) leverages both labeled and unlabeled data to train machine learning (ML) models. We propose the first data augmentation-based membership inference attacks against ML models trained by SSL. Our evaluation shows that the proposed attack can consistently outperform existing membership inference attacks.
  arXiv  Detail & Related papers  (2022-07-25T21:17:24Z)

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.