English
Related papers

Related papers: Beyond Indistinguishability: Measuring Extraction …

200 papers

Logit-based LLM watermarking traces and verifies AI-generated content by maintaining green and red token lists and increasing the likelihood of green tokens during generation. However, it fails in low-entropy scenarios, where predictable…

Computation and Language · Computer Science 2025-05-21 Tianle Gu , Zongqi Wang , Kexin Huang , Yuanqi Yao , Xiangliang Zhang , Yujiu Yang , Xiuying Chen

Large language models (LLMs) are trained on massive corpora that may contain sensitive information, creating privacy risks under membership inference attacks (MIAs). Knowledge distillation is widely used to compress LLMs into smaller…

Machine Learning · Computer Science 2026-01-13 Ziyao Cui , Minxing Zhang , Jian Pei

Differential privacy, a notion of algorithmic stability, is a gold standard for measuring the additional risk an algorithm's output poses to the privacy of a single record in the dataset. Differential privacy is defined as the distance…

Machine Learning · Computer Science 2019-07-05 Kamalika Chaudhuri , Jacob Imola , Ashwin Machanavajjhala

The inference process of modern large language models (LLMs) demands prohibitive computational resources, rendering them infeasible for deployment on consumer-grade devices. To address this limitation, recent studies propose distributed LLM…

Cryptography and Security · Computer Science 2025-05-26 Xinjian Luo , Ting Yu , Xiaokui Xiao

Large language models (LLMs) have been proven capable of memorizing their training data, which can be extracted through specifically designed prompts. As the scale of datasets continues to grow, privacy risks arising from memorization have…

Computation and Language · Computer Science 2023-11-07 Zhenhong Zhou , Jiuyang Xiang , Chaomeng Chen , Sen Su

Large language models (LLMs) have been shown to memorize and reproduce content from their training data, raising significant privacy concerns, especially with web-scale datasets. Existing methods for detecting memorization are primarily…

Cryptography and Security · Computer Science 2026-01-07 Zhenpeng Wu , Jian Lou , Zibin Zheng , Chuan Chen

Large Language Models (LLMs) have demonstrated remarkable capabilities across a wide range of tasks, yet they also exhibit memorization of their training data. This phenomenon raises critical questions about model behavior, privacy risks,…

Machine Learning · Computer Science 2025-12-15 Alexander Xiong , Xuandong Zhao , Aneesh Pappu , Dawn Song

Large language models (LLMs) have demonstrated immense utility across various industries. However, as LLMs advance, the risk of harmful outputs increases due to incorrect or malicious instruction prompts. While current methods effectively…

Computation and Language · Computer Science 2025-06-19 Xinyi Zeng , Yuying Shang , Jiawei Chen , Jingyuan Zhang , Yu Tian

Autoregressive language models (ARMs) have been shown to memorize and occasionally reproduce training data verbatim, raising concerns about privacy and copyright liability. Diffusion language models (DLMs) have recently emerged as a…

Computation and Language · Computer Science 2026-03-04 Xiaoyu Luo , Wenrui Yu , Qiongxiu Li , Johannes Bjerva

Concern about how to aggregate sensitive user data without compromising individual privacy is a major barrier to greater availability of data. The model of differential privacy has emerged as an accepted model to release sensitive…

Databases · Computer Science 2017-10-03 Graham Cormode , Tejas Kulkarni , Divesh Srivastava

Individuals and businesses have been significantly benefited by Large Language Models (LLMs) including PaLM, Gemini and ChatGPT in various ways. For example, LLMs enhance productivity, reduce costs, and enable us to focus on more valuable…

Cryptography and Security · Computer Science 2025-03-03 Xiaojin Zhang , Yahao Pang , Yan Kang , Wei Chen , Lixin Fan , Hai Jin , Qiang Yang

In this work, we address the problem of text anonymization where the goal is to prevent adversaries from correctly inferring private attributes of the author, while keeping the text utility, i.e., meaning and semantics. We propose…

Cryptography and Security · Computer Science 2025-02-04 Ahmed Frikha , Nassim Walha , Krishna Kanth Nakka , Ricardo Mendes , Xue Jiang , Xuebing Zhou

With LLMs increasingly deployed in corporate data management, it is crucial to ensure that these models do not leak sensitive information. In the context of corporate data management, the concept of sensitivity awareness has been…

Cryptography and Security · Computer Science 2026-01-30 Dren Fazlija , Iyiola E. Olatunji , Daniel Kudenko , Sandipan Sikdar

Although Large Language Models (LLMs) have demonstrated strong ability, they are further supposed to be controlled and guided by in real-world scenarios to be safe, accurate, and intelligent. This demands the possession of capability of…

Computation and Language · Computer Science 2024-10-18 Wangtao Sun , Chenxiang Zhang , XueYou Zhang , Xuanqing Yu , Ziyang Huang , Pei Chen , Haotian Xu , Shizhu He , Jun Zhao , Kang Liu

Large Language Models (LLMs) have shown greatly enhanced performance in recent years, attributed to increased size and extensive training data. This advancement has led to widespread interest and adoption across industries and the public.…

Computation and Language · Computer Science 2024-06-19 Victoria Smith , Ali Shahin Shamsabadi , Carolyn Ashurst , Adrian Weller

As machine learning (ML) technologies become more prevalent in privacy-sensitive areas like healthcare and finance, eventually incorporating sensitive information in building data-driven algorithms, it is vital to scrutinize whether these…

Machine Learning · Computer Science 2025-04-08 Ehsanul Kabir , Lucas Craig , Shagufta Mehnaz

For scalable machine learning on large data sets, subsampling a representative subset is a common approach for efficient model training. This is often achieved through importance sampling, whereby informative data points are sampled more…

Cryptography and Security · Computer Science 2025-03-31 Dominik Fay , Sebastian Mair , Jens Sjölund

Large Language Models (LLMs), characterized by being trained on broad amounts of data in a self-supervised manner, have shown impressive performance across a wide range of tasks. Indeed, their generative abilities have aroused interest on…

Machine Learning · Computer Science 2024-07-30 Jorge García-Carrasco , Alejandro Maté , Juan Trujillo

Large Language Models (LLMs) are trained on massive web-crawled corpora. This poses risks of leakage, including personal information, copyrighted texts, and benchmark datasets. Such leakage leads to undermining human trust in AI due to…

Computation and Language · Computer Science 2024-03-26 Masahiro Kaneko , Timothy Baldwin

Local differential privacy (LDP) gives a strong privacy guarantee to be used in a distributed setting like federated learning (FL). LDP mechanisms in FL protect a client's gradient by randomizing it on the client; however, how can we…

Cryptography and Security · Computer Science 2022-06-22 Marin Matsumoto , Tsubasa Takahashi , Seng Pei Liew , Masato Oguchi
‹ Prev 1 4 5 6 7 8 10 Next ›