The Surprising Effectiveness of Membership Inference with Simple N-Gram Coverage

• URL: http://arxiv.org/abs/2508.09603v1
• Date: Wed, 13 Aug 2025 08:35:16 GMT
• Title: The Surprising Effectiveness of Membership Inference with Simple N-Gram Coverage
• Authors: Skyler Hallinan, Jaehun Jung, Melanie Sclar, Ximing Lu, Abhilasha Ravichander, Sahana Ramnath, Yejin Choi, Sai Praneeth Karimireddy, Niloofar Mireshghallah, Xiang Ren,
• Abstract summary: We introduce N-Gram Coverage Attack, a membership inference attack that relies solely on text outputs from the target model.<n>We first demonstrate on a diverse set of existing benchmarks that N-Gram Coverage Attack outperforms other black-box methods.<n>We find that more recent models, such as GPT-4o, exhibit increased robustness to membership inference.
• Score: 71.8564105095189
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Membership inference attacks serves as useful tool for fair use of language models, such as detecting potential copyright infringement and auditing data leakage. However, many current state-of-the-art attacks require access to models' hidden states or probability distribution, which prevents investigation into more widely-used, API-access only models like GPT-4. In this work, we introduce N-Gram Coverage Attack, a membership inference attack that relies solely on text outputs from the target model, enabling attacks on completely black-box models. We leverage the observation that models are more likely to memorize and subsequently generate text patterns that were commonly observed in their training data. Specifically, to make a prediction on a candidate member, N-Gram Coverage Attack first obtains multiple model generations conditioned on a prefix of the candidate. It then uses n-gram overlap metrics to compute and aggregate the similarities of these outputs with the ground truth suffix; high similarities indicate likely membership. We first demonstrate on a diverse set of existing benchmarks that N-Gram Coverage Attack outperforms other black-box methods while also impressively achieving comparable or even better performance to state-of-the-art white-box attacks - despite having access to only text outputs. Interestingly, we find that the success rate of our method scales with the attack compute budget - as we increase the number of sequences generated from the target model conditioned on the prefix, attack performance tends to improve. Having verified the accuracy of our method, we use it to investigate previously unstudied closed OpenAI models on multiple domains. We find that more recent models, such as GPT-4o, exhibit increased robustness to membership inference, suggesting an evolving trend toward improved privacy protections.

Related papers

• No Query, No Access [50.18709429731724]
  We introduce the textbfVictim Data-based Adrial Attack (VDBA), which operates using only victim texts.<n>To prevent access to the victim model, we create a shadow dataset with publicly available pre-trained models and clustering methods.<n>Experiments on the Emotion and SST5 datasets show that VDBA outperforms state-of-the-art methods, achieving an ASR improvement of 52.08%.
  arXiv  Detail & Related papers  (2025-05-12T06:19:59Z)
• Attack-in-the-Chain: Bootstrapping Large Language Models for Attacks Against Black-box Neural Ranking Models [111.58315434849047]
  We introduce a novel ranking attack framework named Attack-in-the-Chain.<n>It tracks interactions between large language models (LLMs) and Neural ranking models (NRMs) based on chain-of-thought.<n> Empirical results on two web search benchmarks show the effectiveness of our method.
  arXiv  Detail & Related papers  (2024-12-25T04:03:09Z)
• An Interpretable N-gram Perplexity Threat Model for Large Language Model Jailbreaks [87.64278063236847]
  In this work, we propose a unified threat model for the principled comparison of jailbreak attacks.<n>Our threat model checks if a given jailbreak is likely to occur in the distribution of text.<n>We adapt popular attacks to this threat model, and, for the first time, benchmark these attacks on equal footing with it.
  arXiv  Detail & Related papers  (2024-10-21T17:27:01Z)
• AdvQDet: Detecting Query-Based Adversarial Attacks with Adversarial Contrastive Prompt Tuning [93.77763753231338]
  Adversarial Contrastive Prompt Tuning (ACPT) is proposed to fine-tune the CLIP image encoder to extract similar embeddings for any two intermediate adversarial queries. We show that ACPT can detect 7 state-of-the-art query-based attacks with $>99%$ detection rate within 5 shots. We also show that ACPT is robust to 3 types of adaptive attacks.
  arXiv  Detail & Related papers  (2024-08-04T09:53:50Z)
• Defense Against Model Extraction Attacks on Recommender Systems [53.127820987326295]
  We introduce Gradient-based Ranking Optimization (GRO) to defend against model extraction attacks on recommender systems. GRO aims to minimize the loss of the protected target model while maximizing the loss of the attacker's surrogate model. Results show GRO's superior effectiveness in defending against model extraction attacks.
  arXiv  Detail & Related papers  (2023-10-25T03:30:42Z)
• Practical Membership Inference Attacks Against Large-Scale Multi-Modal Models: A Pilot Study [17.421886085918608]
  Membership inference attacks (MIAs) aim to infer whether a data point has been used to train a machine learning model. These attacks can be employed to identify potential privacy vulnerabilities and detect unauthorized use of personal data. This paper takes a first step towards developing practical MIAs against large-scale multi-modal models.
  arXiv  Detail & Related papers  (2023-09-29T19:38:40Z)
• Defense-Prefix for Preventing Typographic Attacks on CLIP [14.832208701208414]
  Some adversarial attacks fool a model into false or absurd classifications. We introduce our simple yet effective method: Defense-Prefix (DP), which inserts the DP token before a class name to make words "robust" against typographic attacks. Our method significantly improves the accuracy of classification tasks for typographic attack datasets, while maintaining the zero-shot capabilities of the model.
  arXiv  Detail & Related papers  (2023-04-10T11:05:20Z)
• Ensemble-based Blackbox Attacks on Dense Prediction [16.267479602370543]
  We show that a carefully designed ensemble can create effective attacks for a number of victim models. In particular, we show that normalization of the weights for individual models plays a critical role in the success of the attacks. Our proposed method can also generate a single perturbation that can fool multiple blackbox detection and segmentation models simultaneously.
  arXiv  Detail & Related papers  (2023-03-25T00:08:03Z)
• Label-Only Model Inversion Attacks via Boundary Repulsion [12.374249336222906]
  We introduce an algorithm to invert private training data using only the target model's predicted labels. Using the example of face recognition, we show that the images reconstructed by BREP-MI successfully reproduce the semantics of the private training data.
  arXiv  Detail & Related papers  (2022-03-03T18:57:57Z)

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.