English
Related papers

Related papers: Does Data Contamination Detection Work (Well) for …

200 papers

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…

Machine Learning · Computer Science 2025-10-10 Jiashu Tao , Reza Shokri

The wide adoption and application of Masked language models~(MLMs) on sensitive data (from legal to medical) necessitates a thorough quantitative investigation into their privacy vulnerabilities -- to what extent do MLMs leak information…

Machine Learning · Computer Science 2022-11-07 Fatemehsadat Mireshghallah , Kartik Goyal , Archit Uniyal , Taylor Berg-Kirkpatrick , Reza Shokri

This study investigates the efficacy of Large Language Models (LLMs) in causal discovery. Using newly available open-source LLMs, OLMo and BLOOM, which provide access to their pre-training corpora, we investigate how LLMs address causal…

Computation and Language · Computer Science 2025-10-13 Tao Feng , Lizhen Qu , Niket Tandon , Zhuang Li , Xiaoxi Kang , Gholamreza Haffari

Diffusion Language Models (DLMs) represent a promising alternative to autoregressive language models, using bidirectional masked token prediction. Yet their susceptibility to privacy leakage via Membership Inference Attacks (MIA) remains…

Machine Learning · Computer Science 2026-02-10 Yuetian Chen , Kaiyuan Zhang , Yuntao Du , Edoardo Stoppa , Charles Fleming , Ashish Kundu , Bruno Ribeiro , Ninghui Li

Instruction fine-tuning attacks pose a serious threat to large language models (LLMs) by subtly embedding poisoned examples in fine-tuning datasets, leading to harmful or unintended behaviors in downstream applications. Detecting such…

Machine Learning · Computer Science 2026-02-02 Jiawei Li

Membership inference attacks (MIAs) have been extensively studied in large language models (LLMs) and vision-language models (VLMs), yet their implications for vision-language-action (VLA) models remain largely unexplored. VLA models differ…

Cryptography and Security · Computer Science 2026-05-11 Yuefeng Peng , Mingzhe Li , Kejing Xia , Renhao Zhang , Amir Houmansadr

Membership inference attacks (MIAs) aim to determine whether a specific example was used to train a given language model. While prior work has explored prompt-based attacks such as ReCALL, these methods rely heavily on the assumption that…

Computation and Language · Computer Science 2026-01-27 Gyuwan Kim , Yang Li , Evangelia Spiliopoulou , Jie Ma , William Yang Wang

Large language models (LLMs) are known to be trained on vast amounts of data, which may unintentionally or intentionally include data from commonly used benchmarks. This inclusion can lead to cheatingly high scores on model leaderboards,…

Computation and Language · Computer Science 2025-03-19 Huixuan Zhang , Yun Lin , Xiaojun Wan

Adapting Large Language Models (LLMs) to specific tasks introduces concerns about computational efficiency, prompting an exploration of efficient methods such as In-Context Learning (ICL). However, the vulnerability of ICL to privacy…

Cryptography and Security · Computer Science 2024-09-04 Rui Wen , Zheng Li , Michael Backes , Yang Zhang

Large Language Models (LLMs) are rapidly gaining enormous popularity in recent years. However, the training of LLMs has raised significant privacy and legal concerns, particularly regarding the distillation and inclusion of copyrighted…

Machine Learning · Statistics 2025-10-07 Yinpeng Cai , Lexin Li , Linjun Zhang

The rapid advancement of Large Language Models (LLMs) has been driven by extensive datasets that may contain sensitive information, raising serious privacy concerns. One notable threat is the Membership Inference Attack (MIA), where…

Cryptography and Security · Computer Science 2025-12-17 Yihan Liao , Jacky Keung , Xiaoxue Ma , Jingyu Zhang , Yicheng Sun

Large language models (LLMs) offer impressive performance in various zero-shot and few-shot tasks. However, their success in zero-shot and few-shot settings may be affected by task contamination, a potential limitation that has not been…

Computation and Language · Computer Science 2024-01-02 Changmao Li , Jeffrey Flanigan

As the scale of training corpora for large language models (LLMs) grows, model developers become increasingly reluctant to disclose details on their data. This lack of transparency poses challenges to scientific evaluation and ethical…

Computation and Language · Computer Science 2025-05-22 Weichao Zhang , Ruqing Zhang , Jiafeng Guo , Maarten de Rijke , Yixing Fan , Xueqi Cheng

The rapid advancement of large language models (LLMs) has heightened concerns about benchmark data contamination (BDC), where models inadvertently memorize evaluation data during the training process, inflating performance metrics, and…

Computation and Language · Computer Science 2025-09-23 Cheng Xu , Nan Yan , Shuhao Guan , Changhong Jin , Yuke Mei , Yibing Guo , M-Tahar Kechadi

Machine learning models can leak private information about their training data. The standard methods to measure this privacy risk, based on membership inference attacks (MIAs), only check if a given data point \textit{exactly} matches a…

Machine Learning · Computer Science 2025-09-11 Jiashu Tao , Reza Shokri

Large Language Models (LLMs) and Vision-Language Models (VLMs) have made significant advancements in a wide range of natural language processing and vision-language tasks. Access to large web-scale datasets has been a key factor in their…

Machine Learning · Computer Science 2024-10-18 Jie Ren , Kangrui Chen , Chen Chen , Vikash Sehwag , Yue Xing , Jiliang Tang , Lingjuan Lyu

Training Data Detection (TDD) is a task aimed at determining whether a specific data instance is used to train a machine learning model. In the computer security literature, TDD is also referred to as Membership Inference Attack (MIA).…

Cryptography and Security · Computer Science 2025-08-12 Zhihao Zhu , Yi Yang , Defu Lian

Automatic evaluation methods for large language models (LLMs) are hindered by data contamination, leading to inflated assessments of their effectiveness. Existing strategies, which aim to detect contaminated texts, focus on quantifying…

Computation and Language · Computer Science 2024-06-04 Zhuohao Yu , Chang Gao , Wenjin Yao , Yidong Wang , Wei Ye , Jindong Wang , Xing Xie , Yue Zhang , Shikun Zhang

Membership Inference attacks (MIAs) aim to predict whether a data sample was present in the training data of a machine learning model or not, and are widely used for assessing the privacy risks of language models. Most existing attacks rely…

Computation and Language · Computer Science 2023-08-08 Justus Mattern , Fatemehsadat Mireshghallah , Zhijing Jin , Bernhard Schölkopf , Mrinmaya Sachan , Taylor Berg-Kirkpatrick

Large language models are rapidly transforming social science research by enabling the automation of labor-intensive tasks like data annotation and text analysis. However, LLM outputs vary significantly depending on the implementation…

Computation and Language · Computer Science 2025-10-07 Joachim Baumann , Paul Röttger , Aleksandra Urman , Albert Wendsjö , Flor Miriam Plaza-del-Arco , Johannes B. Gruber , Dirk Hovy
‹ Prev 1 3 4 5 6 7 10 Next ›