English
Related papers

Related papers: Beyond Indistinguishability: Measuring Extraction …

200 papers

Latent feature models (LFM)s are widely employed for extracting latent structures of data. While offering high, parameter estimation is difficult with LFMs because of the combinational nature of latent features, and non-identifiability is a…

Machine Learning · Computer Science 2018-09-27 Ryota Suzuki , Shingo Takahashi , Murtuza Petladwala , Shigeru Kohmoto

Large language models (LLMs) increasingly rely on retrieving information from external corpora. This creates a new attack surface: indirect prompt injection (IPI), where hidden instructions are planted in the corpora and hijack model…

Cryptography and Security · Computer Science 2026-01-13 Hongyan Chang , Ergute Bao , Xinjian Luo , Ting Yu

Collaborative inference in next-generation networks can enhance Artificial Intelligence (AI) applications, including autonomous driving, personal identification, and activity classification. This method involves a three-stage process: a)…

Information Theory · Computer Science 2024-06-04 Mohamed Seif , Yuqi Nie , Andrea Goldsmith , Vincent Poor

The widespread usage of online Large Language Models (LLMs) inference services has raised significant privacy concerns about the potential exposure of private information in user inputs to malicious eavesdroppers. Existing privacy…

Cryptography and Security · Computer Science 2025-05-29 Ziqian Zeng , Jianwei Wang , Junyao Yang , Zhengdong Lu , Haoran Li , Huiping Zhuang , Cen Chen

Recent advances in Large Language Models (LLMs) have enabled them to overcome their context window limitations, and demonstrate exceptional retrieval and reasoning capacities on longer context. Quesion-answering systems augmented with…

Computation and Language · Computer Science 2024-11-19 Zixiong Wang , Gaoyang Liu , Yang Yang , Chen Wang

As large language models increasingly memorize web-scraped training content, they risk exposing copyrighted or private information. Existing protections require compliance from crawlers or model developers, fundamentally limiting their…

Cryptography and Security · Computer Science 2025-12-17 Ruixuan Liu , Toan Tran , Tianhao Wang , Hongsheng Hu , Shuo Wang , Li Xiong

The system prompt in Large Language Models (LLMs) plays a pivotal role in guiding model behavior and response generation. Often containing private configuration details, user roles, and operational instructions, the system prompt has become…

Cryptography and Security · Computer Science 2025-06-02 Badhan Chandra Das , M. Hadi Amini , Yanzhao Wu

As large AI models become increasingly valuable assets, the risk of model weight exfiltration from inference servers grows accordingly. An attacker controlling an inference server may exfiltrate model weights by hiding them within ordinary…

Cryptography and Security · Computer Science 2026-03-16 Roy Rinberg , Adam Karvonen , Alexander Hoover , Daniel Reuter , Keri Warr

In this paper, we design user-centric obfuscation mechanisms that impose the minimum utility loss for guaranteeing user's privacy. We optimize utility subject to a joint guarantee of differential privacy (indistinguishability) and…

Cryptography and Security · Computer Science 2015-05-29 Reza Shokri

We study the problem of in-context learning (ICL) with large language models (LLMs) on private datasets. This scenario poses privacy risks, as LLMs may leak or regurgitate the private examples demonstrated in the prompt. We propose a novel…

Unreadable code could be a breeding ground for errors. Thus, previous work defined approaches based on machine learning to automatically assess code readability that can warn developers when some code artifacts (e.g., classes) become…

Software Engineering · Computer Science 2025-03-12 Antonio Vitale , Emanuela Guglielmi , Rocco Oliveto , Simone Scalabrino

Interpretable predictions, where it is clear why a machine learning model has made a particular decision, can compromise privacy by revealing the characteristics of individual data points. This raises the central question addressed in this…

Machine Learning · Computer Science 2020-04-07 Frederik Harder , Matthias Bauer , Mijung Park

Large language models (LLMs) have emerged as a cornerstone in real-world applications with lengthy streaming inputs (e.g., LLM-driven agents). However, existing LLMs, pre-trained on sequences with a restricted maximum length, cannot process…

Computation and Language · Computer Science 2024-05-29 Chaojun Xiao , Pengle Zhang , Xu Han , Guangxuan Xiao , Yankai Lin , Zhengyan Zhang , Zhiyuan Liu , Maosong Sun

Over the last decade there have been great strides made in developing techniques to compute functions privately. In particular, Differential Privacy gives strong promises about conclusions that can be drawn about an individual. In contrast,…

Databases · Computer Science 2015-03-17 Graham Cormode

In recent years, Local Differential Privacy (LDP), a robust privacy-preserving methodology, has gained widespread adoption in real-world applications. With LDP, users can perturb their data on their devices before sending it out for…

Machine Learning · Computer Science 2023-08-02 Héber H. Arcolezi , Karima Makhlouf , Catuscia Palamidessi

With the increasing adoption of Large Language Models (LLMs), more customization is needed to ensure privacy-preserving and safe generation. We address this objective from two critical aspects: unlearning of sensitive information and…

Machine Learning · Computer Science 2025-10-17 Fatmazohra Rezkellah , Ramzi Dakhmouche

Interpretable text representations should expose coordinates that are not only predictive, but also meaningful enough for independent auditors to apply. Existing discriminative representations often use anonymous embedding directions, while…

Computation and Language · Computer Science 2026-05-21 Tong Wang , Yiqing Xu , Leo Yang Yang

Language Model (LM) agents are increasingly used in complex open-ended decision-making tasks, from AI coding to physical AI. A core requirement in these settings is the ability to both explore the problem space and exploit acquired…

Artificial Intelligence · Computer Science 2026-04-16 Jaden Park , Jungtaek Kim , Jongwon Jeong , Robert D. Nowak , Kangwook Lee , Yong Jae Lee

Pre-trained language models (PLMs) have demonstrated significant proficiency in solving a wide range of general natural language processing (NLP) tasks. Researchers have observed a direct correlation between the performance of these models…

Computation and Language · Computer Science 2024-04-12 Kennedy Edemacu , Xintao Wu

Training reliable deep learning models which avoid making overconfident but incorrect predictions is a longstanding challenge. This challenge is further exacerbated when learning has to be differentially private: protection provided to…

Machine Learning · Computer Science 2023-05-31 Stephan Rabanser , Anvith Thudi , Abhradeep Thakurta , Krishnamurthy Dvijotham , Nicolas Papernot