English
Related papers

Related papers: PATCH: Mitigating PII Leakage in Language Models w…

200 papers

Adversarial attacks by malicious users that threaten the safety of large language models (LLMs) can be viewed as attempts to infer a target property $T$ that is unknown when an instruction is issued, and becomes knowable only after the…

Cryptography and Security · Computer Science 2025-10-21 Masahiro Kaneko , Timothy Baldwin

Explainable Artificial Intelligence (XAI) is a crucial pathway in mitigating the risk of non-transparency in the decision-making process of black-box Artificial Intelligence (AI) systems. However, despite the benefits, XAI methods are found…

Artificial Intelligence · Computer Science 2025-12-30 Sonal Allana , Rozita Dara , Xiaodong Lin , Pulei Xiong

Recent studies have discovered that large language models (LLM) may be ``fooled'' to output private information, including training data, system prompts, and personally identifiable information, under carefully crafted adversarial prompts.…

Cryptography and Security · Computer Science 2025-08-11 Yuzhou Nie , Zhun Wang , Ye Yu , Xian Wu , Xuandong Zhao , Wenbo Guo , Dawn Song

Differential Privacy (DP) is a family of definitions that bound the worst-case privacy leakage of a mechanism. One important feature of the worst-case DP guarantee is it naturally implies protections against adversaries with less prior…

Cryptography and Security · Computer Science 2025-07-14 Marika Swanberg , Meenatchi Sundaram Muthu Selva Annamalai , Jamie Hayes , Borja Balle , Adam Smith

The proliferation of Large Language Models (LLMs) has driven considerable interest in fine-tuning them with domain-specific data to create specialized language models. Nevertheless, such domain-specific fine-tuning data often contains…

Computation and Language · Computer Science 2024-10-29 Yijia Xiao , Yiqiao Jin , Yushi Bai , Yue Wu , Xianjun Yang , Xiao Luo , Wenchao Yu , Xujiang Zhao , Yanchi Liu , Quanquan Gu , Haifeng Chen , Wei Wang , Wei Cheng

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 for Code (LLMs4Code) have achieved strong performance in code generation, but recent studies reveal that they may memorize and leak sensitive information contained in training data, posing serious privacy risks. To…

Cryptography and Security · Computer Science 2026-01-29 Shanzhi Gu , Zhaoyang Qu , Ruotong Geng , Mingyang Geng , Shangwen Wang , Chuanfu Xu , Haotian Wang , Zhipeng Lin , Dezun Dong

In-context learning (ICL) in Large Language Models (LLMs) has shown remarkable performance across various tasks without requiring fine-tuning. However, recent studies have highlighted the risk of private data leakage through the prompt in…

Artificial Intelligence · Computer Science 2025-09-16 Seongho Joo , Hyukhun Koh , Kyomin Jung

Prompt caching in large language models (LLMs) results in data-dependent timing variations: cached prompts are processed faster than non-cached prompts. These timing differences introduce the risk of side-channel timing attacks. For…

Computation and Language · Computer Science 2025-07-15 Chenchen Gu , Xiang Lisa Li , Rohith Kuditipudi , Percy Liang , Tatsunori Hashimoto

Differential privacy (DP) is a formal privacy framework that enables training machine learning (ML) models while protecting individuals' data. As pointed out by prior work, ML models are part of larger systems, which can lead to so-called…

Machine Learning · Computer Science 2026-04-27 Marlon Tobaben , Talal Alrawajfeh , Marcus Klasson , Mikko Heikkilä , Arno Solin , Antti Honkela

Privacy vulnerabilities in LLMs, such as leakage from memorization, have been constantly identified, and various mitigation proposals have been proposed. LoRA is usually used in fine-tuning LLMs and a good entry point to insert…

Cryptography and Security · Computer Science 2024-10-25 Yulian Sun , Li Duan , Yong Li

Prompt-tuning has received attention as an efficient tuning method in the language domain, i.e., tuning a prompt that is a few tokens long, while keeping the large language model frozen, yet achieving comparable performance with…

Cryptography and Security · Computer Science 2023-04-18 Shangyu Xie , Wei Dai , Esha Ghosh , Sambuddha Roy , Dan Schwartz , Kim Laine

Differential privacy (DP) is applied when fine-tuning pre-trained large language models (LLMs) to limit leakage of training examples. While most DP research has focused on improving a model's privacy-utility tradeoff, some find that DP can…

Computation and Language · Computer Science 2024-10-25 Md. Khairul Islam , Andrew Wang , Tianhao Wang , Yangfeng Ji , Judy Fox , Jieyu Zhao

Large language models (LLMs) are increasingly being used in privacy pipelines to detect and remedy sensitive data leakage. These solutions often rely on the premise that LLMs can reliably recognize human names, one of the most important…

Cryptography and Security · Computer Science 2026-04-28 Dzung Pham , Peter Kairouz , Niloofar Mireshghallah , Eugene Bagdasarian , Chau Minh Pham , Amir Houmansadr

Side-channel attacks on shared hardware resources increasingly threaten confidentiality, especially with the rise of Large Language Models (LLMs). In this work, we introduce Spill The Beans, a novel application of cache side-channels to…

Cryptography and Security · Computer Science 2025-05-05 Andrew Adiletta , Berk Sunar

Large language models (LLMs) trained on web-scale corpora can memorize sensitive training data, posing significant privacy risks. Differential privacy (DP) has emerged as a principled framework that limits the influence of individual data…

Computation and Language · Computer Science 2026-05-13 Eduardo Tenorio , Karuna Bhaila , Xintao Wu

To continuously improve quality and reflect changes in data, machine learning applications have to regularly retrain and update their core models. We show that a differential analysis of language model snapshots before and after an update…

Recent large-scale natural language processing (NLP) systems use a pre-trained Large Language Model (LLM) on massive and diverse corpora as a headstart. In practice, the pre-trained model is adapted to a wide array of tasks via fine-tuning…

Computation and Language · Computer Science 2022-09-12 Jimit Majmudar , Christophe Dupuy , Charith Peris , Sami Smaili , Rahul Gupta , Richard Zemel

Machine learning models are known to memorize the unique properties of individual data points in a training set. This memorization capability can be exploited by several types of attacks to infer information about the training data, most…

Information Theory · Computer Science 2021-04-19 Sara Saeidian , Giulia Cervia , Tobias J. Oechtering , Mikael Skoglund

Large Language Models (LLMs) have demonstrated extraordinary capabilities and contributed to multiple fields, such as generating and summarizing text, language translation, and question-answering. Nowadays, LLM is becoming a very popular…

Computation and Language · Computer Science 2024-11-18 Badhan Chandra Das , M. Hadi Amini , Yanzhao Wu