English
Related papers

Related papers: AST-PAC: AST-guided Membership Inference for Code

200 papers

Large Language Models (LLMs) have the promise to revolutionize computing broadly, but their complexity and extensive training data also expose significant privacy vulnerabilities. One of the simplest privacy risks associated with LLMs is…

Machine Learning · Computer Science 2024-09-25 Rongting Zhang , Martin Bertran , Aaron Roth

Abstract syntax tree (AST) mapping algorithms are widely used to analyze changes in source code. Despite the foundational role of AST mapping algorithms, little effort has been made to evaluate the accuracy of AST mapping algorithms, i.e.,…

Software Engineering · Computer Science 2021-03-02 Yuanrui Fan , Xin Xia , David Lo , Ahmed E. Hassan , Yuan Wang , Shanping Li

Polar coding gives rise to the first explicit family of codes that provably achieve capacity with efficient encoding and decoding for a wide range of channels. However, its performance at short block lengths is far from optimal. Arikan has…

Information Theory · Computer Science 2021-07-21 Hanwen Yao , Arman Fazeli , Alexander Vardy

Large language model-based multi-agent systems (LLM-MAS) effectively accomplish complex and dynamic tasks through inter-agent communication, but this reliance introduces substantial safety vulnerabilities. Existing attack methods targeting…

Cryptography and Security · Computer Science 2025-08-06 Bingyu Yan , Ziyi Zhou , Xiaoming Zhang , Chaozhuo Li , Ruilin Zeng , Yirui Qi , Tianbo Wang , Litian Zhang

Membership Inference Attacks (MIAs) determine whether a specific data point was included in the training set of a target model. In this paper, we introduce the Semantic Membership Inference Attack (SMIA), a novel approach that enhances MIA…

Machine Learning · Computer Science 2024-06-17 Hamid Mozaffari , Virendra J. Marathe

The remarkable success of Large Language Models (LLMs) relies heavily on their substantial scale, which poses significant challenges during model deployment in terms of latency and memory consumption. Recently, numerous studies have…

Computation and Language · Computer Science 2024-12-19 Weiyu Huang , Yuezhou Hu , Guohao Jian , Jun Zhu , Jianfei Chen

Parameter-Efficient Fine-Tuning (PEFT) has become a key strategy for adapting large language models, with recent advances in sparse tuning reducing overhead by selectively updating key parameters or subsets of data. Existing approaches…

Machine Learning · Computer Science 2026-03-11 Kai Yao , Zhenghan Song , Kaixin Wu , Mingjie Zhong , Danzhao Cheng , Zhaorui Tan , Yixin Ji , Penglei Gao

Membership Inference Attacks (MIAs) infer whether a data point is in the training data of a machine learning model. It is a threat while being in the training data is private information of a data point. MIA correctly infers some data…

Cryptography and Security · Computer Science 2022-10-31 Mauro Conti , Jiaxin Li , Stjepan Picek

Membership Inference (MI) poses a substantial privacy threat to the training data of Automatic Speech Recognition (ASR) systems, while also offering an opportunity to audit these models with regard to user data. This paper explores the…

Machine Learning · Computer Science 2024-05-03 Francisco Teixeira , Karla Pizzi , Raphael Olivier , Alberto Abad , Bhiksha Raj , Isabel Trancoso

Large language models (LLMs) show strong performance across many applications, but their ability to memorize and potentially reveal training data raises serious privacy concerns. We introduce the PopQuiz Attack, a black-box membership…

Cryptography and Security · Computer Science 2026-05-08 Zeyuan Chen , Yihan Ma , Xinyue Shen , Michael Backes , Yang Zhang

Recently, a novel variation of polar codes known as polarization-adjusted convolutional (PAC) codes has been introduced by Ar{\i}kan. These codes significantly outperform conventional polar and convolutional codes, particularly for short…

Information Theory · Computer Science 2025-08-15 Mohsen Moradi , Hessam Mahdavifar

Safety classifiers are essential safeguards within generative AI systems, filtering harmful content or identifying at-risk users when interacting with large language models. Despite their necessity, these models are trained on sensitive…

Machine Learning · Computer Science 2026-05-25 Anthony Hughes , Alexander Goldberg , Prince Jha , Adam Perer , Nikolaos Aletras , Niloofar Mireshghallah

Membership inference attacks (MIAs), which enable adversaries to determine whether specific data points were part of a model's training dataset, have emerged as an important framework to understand, assess, and quantify the potential…

Cryptography and Security · Computer Science 2026-03-23 Toan Tran , Olivera Kotevska , Li Xiong

Large language models (LLMs) have become essential tools for digital task assistance. Their training relies heavily on the collection of vast amounts of data, which may include copyright-protected or sensitive information. Recent studies on…

Cryptography and Security · Computer Science 2025-09-22 Sagiv Antebi , Edan Habler , Asaf Shabtai , Yuval Elovici

Attribute-efficient PAC learning of sparse halfspaces has been a fundamental problem in machine learning theory. In recent years, machine learning algorithms are faced with prevalent data corruptions or even malicious attacks. It is of…

Machine Learning · Computer Science 2026-03-06 Shiwei Zeng , Jie Shen

The use of large language models (LLMs) in peer review systems has attracted growing attention, making it essential to examine their potential vulnerabilities. Prior attacks rely on prompt injection, which alters manuscript content and…

Computation and Language · Computer Science 2026-01-13 Masahiro Kaneko

Over-parameterized models are typically vulnerable to membership inference attacks, which aim to determine whether a specific sample is included in the training of a given model. Previous Weight regularizations (e.g., L1 regularization)…

Machine Learning · Computer Science 2024-10-10 Qiang Hu , Hengxiang Zhang , Hongxin Wei

Large language models (LLMs) have achieved remarkable success across diverse applications but remain vulnerable to jailbreak attacks, where attackers craft prompts that bypass safety alignment and elicit unsafe responses. Among existing…

Computation and Language · Computer Science 2026-03-04 Zhi Xu , Jiaqi Li , Xiaotong Zhang , Hong Yu , Han Liu

Detecting parallelizable code regions is a challenging task, even for experienced developers. Numerous recent studies have explored the use of machine learning for code analysis and program synthesis, including parallelization, in light of…

Machine Learning · Computer Science 2024-11-25 Le Chen , Quazi Ishtiaque Mahmud , Hung Phan , Nesreen K. Ahmed , Ali Jannesari

Large language models (LLMs) are effective for automated program repair, but plausible patches that pass the full test suite often rewrite more code than necessary, increasing review and maintenance costs. This over-editing is common…

Software Engineering · Computer Science 2026-04-07 Boyang Yang , Zijian Cai , Shunfu Jin , Haoye Tian