English
Related papers

Related papers: Blackbox Dataset Inference for LLM

200 papers

We might hope that when faced with unexpected inputs, well-designed software systems would fire off warnings. Machine learning (ML) systems, however, which depend strongly on properties of their inputs (e.g. the i.i.d. assumption), tend to…

Machine Learning · Statistics 2019-10-29 Stephan Rabanser , Stephan Günnemann , Zachary C. Lipton

Deep neural networks are susceptible to various inference attacks as they remember information about their training data. We design white-box inference attacks to perform a comprehensive privacy analysis of deep learning models. We measure…

Machine Learning · Statistics 2020-06-09 Milad Nasr , Reza Shokri , Amir Houmansadr

The safety and alignment of Large Language Models (LLMs) are critical for their responsible deployment. Current evaluation methods predominantly focus on identifying and preventing overtly harmful outputs. However, they often fail to…

Machine learning (ML) models have been shown to be vulnerable to Membership Inference Attacks (MIA), which infer the membership of a given data point in the target dataset by observing the prediction output of the ML model. While the key…

Machine Learning · Computer Science 2020-07-28 Shakila Mahjabin Tonni , Dinusha Vatsalan , Farhad Farokhi , Dali Kaafar , Zhigang Lu , Gioacchino Tangari

The memorization of training data in large language models (LLMs) poses significant privacy and copyright concerns. Existing data extraction methods, particularly heuristic-based divergence attacks, often exhibit limited success and offer…

Computation and Language · Computer Science 2025-11-11 Myeongseob Ko , Nikhil Reddy Billa , Adam Nguyen , Charles Fleming , Ming Jin , Ruoxi Jia

Large language models (LLMs) are increasingly trained on massive, heterogeneous text corpora, raising serious concerns about the unauthorised use of proprietary or personal data during model training. In this work, we address the problem of…

Computation and Language · Computer Science 2026-01-08 Ruihan Zhang , Jun Sun

Reliably predicting the behavior of language models -- such as whether their outputs are correct or have been adversarially manipulated -- is a fundamentally challenging task. This is often made even more difficult as frontier language…

Machine Learning · Computer Science 2025-12-02 Dylan Sam , Marc Finzi , J. Zico Kolter

Can large language models introspect, that is, accurately detect perturbations to their own internal states? We systematically investigate this question using activation steering in Meta-Llama-3.1-8B-Instruct. First, we show that the binary…

Artificial Intelligence · Computer Science 2026-03-03 Ely Hahami , Ishaan Sinha , Lavik Jain , Josh Kaplan , Jon Hahami

Large Language Models (LLMs) frequently generate plausible but non-factual content, a phenomenon known as hallucination. While existing detection methods typically rely on computationally expensive sampling-based consistency checks or…

Machine Learning · Computer Science 2026-05-07 Dan Wilson , Mohamed Akrout

High-quality open-source datasets have emerged as a pivotal catalyst driving the swift advancement of deep learning, while facing the looming threat of potential exploitation. Protecting these datasets is of paramount importance for the…

Computer Vision and Pattern Recognition · Computer Science 2025-07-17 Yuechen Xie , Jie Song , Yicheng Shan , Xiaoyan Zhang , Yuanyu Wan , Shengxuming Zhang , Jiarui Duan , Mingli Song

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

This work adapts and studies the gradient-based Membership Inference Test (gMINT) to the classification of text based on LLMs. MINT is a general approach intended to determine if given data was used for training machine learning models, and…

Computation and Language · Computer Science 2025-03-14 Gonzalo Mancera , Daniel DeAlcala , Julian Fierrez , Ruben Tolosana , Aythami Morales

It is commonplace to produce application-specific models by fine-tuning large pre-trained models using a small bespoke dataset. The widespread availability of foundation model checkpoints on the web poses considerable risks, including the…

Cryptography and Security · Computer Science 2024-04-02 Yuxin Wen , Leo Marchyok , Sanghyun Hong , Jonas Geiping , Tom Goldstein , Nicholas Carlini

Membership Inference Attack (MIA) determines the presence of a record in a machine learning model's training data by querying the model. Prior work has shown that the attack is feasible when the model is overfitted to its training data or…

Cryptography and Security · Computer Science 2018-02-15 Yunhui Long , Vincent Bindschaedler , Lei Wang , Diyue Bu , Xiaofeng Wang , Haixu Tang , Carl A. Gunter , Kai Chen

Models can expose sensitive information about their training data. In an attribute inference attack, an adversary has partial knowledge of some training records and access to a model trained on those records, and infers the unknown values…

Cryptography and Security · Computer Science 2022-09-07 Bargav Jayaraman , David Evans

As large language models (LLMs) become an important way of information access, there have been increasing concerns that LLMs may intensify the spread of unethical content, including implicit bias that hurts certain populations without…

Computation and Language · Computer Science 2025-07-14 Yuchen Wen , Keping Bi , Wei Chen , Jiafeng Guo , Xueqi Cheng

Understanding black-box machine learning models is crucial for their widespread adoption. Learning globally interpretable models is one approach, but achieving high performance with them is challenging. An alternative approach is to explain…

Machine Learning · Computer Science 2022-09-23 Jinsung Yoon , Sercan O. Arik , Tomas Pfister

OpenLVLM-MIA is a new benchmark that highlights fundamental challenges in evaluating membership inference attacks (MIA) against large vision-language models (LVLMs). While prior work has reported high attack success rates, our analysis…

Computer Vision and Pattern Recognition · Computer Science 2025-12-03 Ryoto Miyamoto , Xin Fan , Fuyuko Kido , Tsuneo Matsumoto , Hayato Yamana

We consider the problem of auditing black-box large language models (LLMs) to ensure they behave reliably when deployed in production settings, particularly in high-stakes domains such as legal, medical, and regulatory compliance. Existing…

Computation and Language · Computer Science 2025-12-15 Paulius Rauba , Qiyao Wei , Mihaela van der Schaar

Large language models (LLMs) are demonstrating significant promise as an alternate strategy to facilitate analyses and optimizations of high-performance computing programs, circumventing the need for resource-intensive manual tool creation.…

Machine Learning · Computer Science 2023-11-28 Le Chen , Xianzhong Ding , Murali Emani , Tristan Vanderbruggen , Pei-hung Lin , Chuanhua Liao