English
Related papers

Related papers: Mitigating Sensitive Information Leakage in LLMs4C…

200 papers

While cryptographic algorithms such as the ubiquitous Advanced Encryption Standard (AES) are secure, *physical implementations* of these algorithms in hardware inevitably 'leak' sensitive data such as cryptographic keys. A particularly…

Machine Learning · Computer Science 2026-03-26 Jimmy Gammell , Anand Raghunathan , Abolfazl Hashemi , Kaushik Roy

Large language models show impressive abilities in memorizing world knowledge, which leads to concerns regarding memorization of private information, toxic or sensitive knowledge, and copyrighted content. We introduce the problem of Large…

Computation and Language · Computer Science 2025-02-18 Yu Wang , Ruihan Wu , Zexue He , Xiusi Chen , Julian McAuley

Unlearning seeks to remove specific knowledge from large language models (LLMs), but its effectiveness remains contested. On one side, "forgotten" knowledge can often be recovered through interventions such as light fine-tuning; on the…

Computation and Language · Computer Science 2025-09-30 Qingjie Zhang , Haoting Qian , Zhicong Huang , Cheng Hong , Minlie Huang , Ke Xu , Chao Zhang , Han Qiu

Large language models (LLMs) have been widely adopted across various applications, leveraging customized system prompts for diverse tasks. Facing potential system prompt leakage risks, model developers have implemented strategies to prevent…

Cryptography and Security · Computer Science 2025-09-29 Bochuan Cao , Changjiang Li , Yuanpu Cao , Yameng Ge , Ting Wang , Jinghui Chen

The significant advancements in large language models (LLMs) give rise to a promising research direction, i.e., leveraging LLMs as recommenders (LLMRec). The efficacy of LLMRec arises from the open-world knowledge and reasoning capabilities…

Information Retrieval · Computer Science 2024-07-02 Hangyu Wang , Jianghao Lin , Bo Chen , Yang Yang , Ruiming Tang , Weinan Zhang , Yong Yu

Machine unlearning aims to remove specific knowledge (e.g., copyrighted or private data) from a trained model without full retraining. In practice, models are often quantized (e.g., 4-bit) for deployment, but we find that quantization can…

Machine Learning · Computer Science 2026-01-23 Himanshu Mishra , Kanwal Mehreen

Large language models (LLMs) have advanced to encompass extensive knowledge across diverse domains. Yet controlling what a large language model should not know is important for ensuring alignment and thus safe use. However, accurately and…

Computation and Language · Computer Science 2024-11-01 Chris Yuhao Liu , Yaxuan Wang , Jeffrey Flanigan , Yang Liu

Large Language Models (LLMs) have demonstrated remarkable capabilities in natural language understanding and generation. However, their tendency to memorize training data raises concerns regarding privacy, copyright compliance, and…

Machine Learning · Computer Science 2025-06-23 Arjun Dosajh , Mihika Sanghi

In collaborative learning, clients keep their data private and communicate only the computed gradients of the deep neural network being trained on their local data. Several recent attacks show that one can still extract private information…

Machine Learning · Computer Science 2022-07-26 Fan Mo , Anastasia Borovykh , Mohammad Malekzadeh , Soteris Demetriou , Deniz Gündüz , Hamed Haddadi

The past a few years have witnessed the great success of large language models, demonstrating powerful capabilities in comprehending textual data and generating human-like languages. Large language models achieve success by being trained on…

Computation and Language · Computer Science 2025-03-20 Estrid He , Tabinda Sarwar , Ibrahim Khalil , Xun Yi , Ke Wang

The inability to filter out in advance all potentially problematic data from the pre-training of large language models has given rise to the need for methods for unlearning specific pieces of knowledge after training. Existing techniques…

Computation and Language · Computer Science 2026-04-17 Seyun Bae , Seokhan Lee , Eunho Yang

Large language models (LLMs) have significantly transformed natural language understanding and generation, but they raise privacy concerns due to potential exposure of sensitive information. Studies have highlighted the risk of information…

Machine Learning · Computer Science 2025-11-20 Bishnu Bhusal , Manoj Acharya , Ramneet Kaur , Colin Samplawski , Anirban Roy , Adam D. Cobb , Rohit Chadha , Susmit Jha

Cascades are a common type of machine learning systems in which a large, remote model can be queried if a local model is not able to accurately label a user's data by itself. Serving stacks for large language models (LLMs) increasingly use…

Machine Learning · Computer Science 2024-04-03 Florian Hartmann , Duc-Hieu Tran , Peter Kairouz , Victor Cărbune , Blaise Aguera y Arcas

The task of "unlearning" certain concepts in large language models (LLMs) has attracted immense attention recently, due to its importance in mitigating undesirable model behaviours, such as the generation of harmful, private, or incorrect…

Computation and Language · Computer Science 2025-09-03 Yihuai Hong , Lei Yu , Haiqin Yang , Shauli Ravfogel , Mor Geva

Large Language Models (LLMs) offer transformative capabilities for hardware design automation, particularly in Verilog code generation. However, they also pose significant data security challenges, including Verilog evaluation data…

Large language models trained on web-scale corpora can memorize undesirable data containing misinformation, copyrighted material, or private or sensitive information. Recently, several machine unlearning algorithms have been proposed to…

Computation and Language · Computer Science 2025-05-27 Keivan Rezaei , Khyathi Chandu , Soheil Feizi , Yejin Choi , Faeze Brahman , Abhilasha Ravichander

Large language models (LLMs) often memorize private information during training, raising serious privacy concerns. While machine unlearning has emerged as a promising solution, its true effectiveness against privacy attacks remains unclear.…

Machine Learning · Computer Science 2026-04-27 Xiaoyi Chen , Haoyuan Wang , Siyuan Tang , Sijia Liu , Liya Su , XiaoFeng Wang , Haixu Tang

Machine unlearning aims to remove sensitive or undesired data from large language models. However, recent studies suggest that unlearning is often shallow, claiming that removed knowledge can easily be recovered. In this work, we critically…

Machine Learning · Computer Science 2025-06-03 Zhili Feng , Yixuan Even Xu , Alexander Robey , Robert Kirk , Xander Davies , Yarin Gal , Avi Schwarzschild , J. Zico Kolter

Document understanding models have recently demonstrated remarkable performance by leveraging extensive collections of user documents. However, since documents often contain large amounts of personal data, their usage can pose a threat to…

Computer Vision and Pattern Recognition · Computer Science 2024-05-01 Lei Kang , Mohamed Ali Souibgui , Fei Yang , Lluis Gomez , Ernest Valveny , Dimosthenis Karatzas

Large Language Model (LLM) unlearning aims to remove targeted knowledge from a trained model, but practical deployments often require post-training quantization (PTQ) for efficient inference. However, aggressive low-bit PTQ can mask…