English
Related papers

Related papers: PreCurious: How Innocent Pre-Trained Language Mode…

200 papers

Backdoor attacks pose a serious security threat for training neural networks as they surreptitiously introduce hidden functionalities into a model. Such backdoors remain silent during inference on clean inputs, evading detection due to…

Cryptography and Security · Computer Science 2023-12-15 Lukas Struppek , Martin B. Hentschel , Clifton Poth , Dominik Hintersdorf , Kristian Kersting

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

Fine-tuning is arguably the most straightforward way to tailor a pre-trained model (e.g., a foundation model) to downstream applications, but it also comes with the risk of losing valuable knowledge the model had learned in pre-training.…

The pervasive deployment of deep learning models across critical domains has concurrently intensified privacy concerns due to their inherent propensity for data memorization. While Membership Inference Attacks (MIAs) serve as the gold…

Machine Learning · Computer Science 2026-04-16 Chihan Huang , Huaijin Wang , Shuai Wang

The growing use of large language models in sensitive domains has exposed a critical weakness: the inability to ensure that private information can be permanently forgotten. Yet these systems still lack reliable mechanisms to guarantee that…

Machine Learning · Computer Science 2025-11-14 James Jin Kang , Dang Bui , Thanh Pham , Huo-Chong Ling

With the advance of language models, privacy protection is receiving more attention. Training data extraction is therefore of great importance, as it can serve as a potential tool to assess privacy leakage. However, due to the difficulty of…

Computation and Language · Computer Science 2023-06-02 Weichen Yu , Tianyu Pang , Qian Liu , Chao Du , Bingyi Kang , Yan Huang , Min Lin , Shuicheng Yan

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

Membership inference attacks aim to infer whether a data record has been used to train a target model by observing its predictions. In sensitive domains such as healthcare, this can constitute a severe privacy violation. In this work we…

Cryptography and Security · Computer Science 2022-12-05 Tomas Chobola , Dmitrii Usynin , Georgios Kaissis

Fine-tuned language models pose significant privacy risks, as they may memorize and expose sensitive information from their training data. Membership inference attacks (MIAs) provide a principled framework for auditing these risks, yet…

Computation and Language · Computer Science 2026-04-14 David Ilić , David Stanojević , Kostadin Cvejoski

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

The discourse on privacy risks in Large Language Models (LLMs) has disproportionately focused on verbatim memorization of training data, while a constellation of more immediate and scalable privacy threats remain underexplored. This…

Cryptography and Security · Computer Science 2025-10-03 Niloofar Mireshghallah , Tianshi Li

Large language models (LLMs), renowned for their impressive capabilities in various tasks, have significantly advanced artificial intelligence. Yet, these advancements have raised growing concerns about privacy and security implications. To…

Artificial Intelligence · Computer Science 2024-03-28 Yuqi Yang , Xiaowen Huang , Jitao Sang

Adversarial Training (AT) is crucial for obtaining deep neural networks that are robust to adversarial attacks, yet recent works found that it could also make models more vulnerable to privacy attacks. In this work, we further reveal this…

Machine Learning · Computer Science 2022-02-23 Jingyang Zhang , Yiran Chen , Hai Li

In the privacy-utility tradeoff of a model trained on benchmark language and vision tasks, remarkable improvements have been widely reported with the use of pretraining on publicly available data. This is in part due to the benefits of…

Machine Learning · Computer Science 2023-02-21 Arun Ganesh , Mahdi Haghifam , Milad Nasr , Sewoong Oh , Thomas Steinke , Om Thakkar , Abhradeep Thakurta , Lun Wang

Differentially private models seek to protect the privacy of data the model is trained on, making it an important component of model security and privacy. At the same time, data scientists and machine learning engineers seek to use…

Cryptography and Security · Computer Science 2021-03-17 Erick Galinkin

Neural networks are widely known to be vulnerable to backdoor attacks, a method that poisons a portion of the training data to make the target model perform well on normal data sets, while outputting attacker-specified or random categories…

Computer Vision and Pattern Recognition · Computer Science 2024-06-07 Yong Li , Han Gao

The decentralized nature of federated learning, that often leverages the power of edge devices, makes it vulnerable to attacks against privacy and security. The privacy risk for a peer is that the model update she computes on her private…

Cryptography and Security · Computer Science 2021-08-05 Josep Domingo-Ferrer , Alberto Blanco-Justicia , Jesús Manjón , David Sánchez

Federated learning (FL) has become a key component in various language modeling applications such as machine translation, next-word prediction, and medical record analysis. These applications are trained on datasets from many FL…

Cryptography and Security · Computer Science 2025-12-11 Md Rafi Ur Rashid , Vishnu Asutosh Dasu , Kang Gu , Najrin Sultana , Shagufta Mehnaz

As the adoption of explainable AI (XAI) continues to expand, the urgency to address its privacy implications intensifies. Despite a growing corpus of research in AI privacy and explainability, there is little attention on privacy-preserving…

Cryptography and Security · Computer Science 2024-06-27 Thanh Tam Nguyen , Thanh Trung Huynh , Zhao Ren , Thanh Toan Nguyen , Phi Le Nguyen , Hongzhi Yin , Quoc Viet Hung Nguyen

Large language models (LLMs) are vulnerable when trained on datasets containing harmful content, which leads to potential jailbreaking attacks in two scenarios: the integration of harmful texts within crowdsourced data used for pre-training…

Cryptography and Security · Computer Science 2024-06-03 Xiaoqun Liu , Jiacheng Liang , Muchao Ye , Zhaohan Xi