English
Related papers

Related papers: Extracted BERT Model Leaks More Information than Y…

200 papers

Model-serving systems have become increasingly popular, especially in real-time web applications. In such systems, users send queries to the server and specify the desired performance metrics (e.g., desired accuracy, latency). The server…

Cryptography and Security · Computer Science 2023-08-08 Debopam Sanyal , Jui-Tse Hung , Manav Agrawal , Prahlad Jasti , Shahab Nikkhoo , Somesh Jha , Tianhao Wang , Sibin Mohan , Alexey Tumanov

Differential privacy provides strong privacy guarantees for machine learning applications. Much recent work has been focused on developing differentially private models, however there has been a gap in other stages of the machine learning…

Machine Learning · Computer Science 2021-09-07 Ashly Lau , Jonathan Passerat-Palmbach

Due to the correlational structure in our traits such as identities, cultures, and political attitudes, seemingly innocuous preferences like following a band or using a specific slang can reveal private traits. This possibility, especially…

Social and Information Networks · Computer Science 2026-03-16 Byunghwee Lee , Sangyeon Kim , Filippo Menczer , Yong-Yeol Ahn , Haewoon Kwak , Jisun An

Machine learning models trained on confidential datasets are increasingly being deployed for profit. Machine Learning as a Service (MLaaS) has made such models easily accessible to end-users. Prior work has developed model extraction…

Machine Learning · Computer Science 2019-05-23 Soham Pal , Yash Gupta , Aditya Shukla , Aditya Kanade , Shirish Shevade , Vinod Ganapathy

Neural networks are often trained on proprietary datasets, making them attractive attack targets. We present a novel dataset extraction method leveraging an innovative training time backdoor attack, allowing a malicious federated learning…

Cryptography and Security · Computer Science 2025-12-19 Eden Luzon , Guy Amit , Roy Weiss , Torsten Kraub , Alexandra Dmitrienko , Yisroel Mirsky

Recent work has demonstrated the successful extraction of training data from generative language models. However, it is not evident whether such extraction is feasible in text classification models since the training objective is to predict…

Computation and Language · Computer Science 2022-06-10 Adel Elmahdy , Huseyin A. Inan , Robert Sim

Retrieval-Augmented Generation (RAG) improves pre-trained models by incorporating external knowledge at test time to enable customized adaptation. We study the risk of datastore leakage in Retrieval-In-Context RAG Language Models (LMs). We…

Computation and Language · Computer Science 2024-10-08 Zhenting Qi , Hanlin Zhang , Eric Xing , Sham Kakade , Himabindu Lakkaraju

Increasing model size when pretraining natural language representations often results in improved performance on downstream tasks. However, at some point further model increases become harder due to GPU/TPU memory limitations and longer…

Computation and Language · Computer Science 2020-02-11 Zhenzhong Lan , Mingda Chen , Sebastian Goodman , Kevin Gimpel , Piyush Sharma , Radu Soricut

The increasing demand for domain-specific and human-aligned Large Language Models (LLMs) has led to the widespread adoption of Supervised Fine-Tuning (SFT) techniques. SFT datasets often comprise valuable instruction-response pairs, making…

Cryptography and Security · Computer Science 2025-06-24 Zongjie Li , Daoyuan Wu , Shuai Wang , Zhendong Su

This work quantifies the risk of training data leakage from LLMs (Large Language Models) using sequence-level probabilities. Computing extraction probabilities for individual sequences provides finer-grained information than has been…

Computation and Language · Computer Science 2025-04-17 Trishita Tiwari , G. Edward Suh

It is challenging to control the quality of online information due to the lack of supervision over all the information posted online. Manual checking is almost impossible given the vast number of posts made on online media and how quickly…

Computation and Language · Computer Science 2022-03-16 Rini Anggrainingsih , Ghulam Mubashar Hassan , Amitava Datta

The prosperity of machine learning has also brought people's concerns about data privacy. Among them, inference attacks can implement privacy breaches in various MLaaS scenarios and model training/prediction phases. Specifically, inference…

Machine Learning · Computer Science 2024-06-28 Feng Wu , Lei Cui , Shaowen Yao , Shui Yu

While open Large Language Models (LLMs) have made significant progress, they still fall short of matching the performance of their closed, proprietary counterparts, making the latter attractive even for the use on highly private data.…

Machine Learning · Computer Science 2024-11-18 Vincent Hanke , Tom Blanchard , Franziska Boenisch , Iyiola Emmanuel Olatunji , Michael Backes , Adam Dziedzic

This paper studies model-inversion attacks, in which the access to a model is abused to infer information about the training data. Since its first introduction, such attacks have raised serious concerns given that training data usually…

Machine Learning · Computer Science 2020-04-21 Yuheng Zhang , Ruoxi Jia , Hengzhi Pei , Wenxiao Wang , Bo Li , Dawn Song

Although large language models have demonstrated the potential for personalized advertising recommendations in experimental environments, in actual operations, how advertising recommendation systems can be combined with measures such as…

Computation and Language · Computer Science 2025-05-09 Haoyang Feng , Yanjun Dai , Yuan Gao

Significant advancements have recently been made in large language models represented by GPT models. Users frequently have multi-round private conversations with cloud-hosted GPT models for task optimization. Yet, this operational paradigm…

Cryptography and Security · Computer Science 2024-10-08 Junjie Chu , Zeyang Sha , Michael Backes , Yang Zhang

In the current landscape of language model research, larger models, larger datasets and more compute seems to be the only way to advance towards intelligence. While there have been extensive studies of scaling laws and models' scaling…

Computation and Language · Computer Science 2024-08-01 Muhammad Ali , Swetasudha Panda , Qinlan Shen , Michael Wick , Ari Kobren

Large Language Models (LLMs) demonstrate impressive capabilities across various fields, yet their increasing use raises critical security concerns. This article reviews recent literature addressing key issues in LLM security, with a focus…

Cryptography and Security · Computer Science 2025-11-26 Benji Peng , Keyu Chen , Ming Li , Pohsun Feng , Ziqian Bi , Junyu Liu , Xinyuan Song , Qian Niu

Large multimodal language models have proven transformative in numerous applications. However, these models have been shown to memorize and leak pre-training data, raising serious user privacy and information security concerns. While data…

Computation and Language · Computer Science 2023-10-04 Yang Chen , Ethan Mendes , Sauvik Das , Wei Xu , Alan Ritter

Federated learning is considered as an effective privacy-preserving learning mechanism that separates the client's data and model training process. However, federated learning is still under the risk of privacy leakage because of the…

Machine Learning · Computer Science 2022-06-03 Yuxuan Wan , Han Xu , Xiaorui Liu , Jie Ren , Wenqi Fan , Jiliang Tang