English
Related papers

Related papers: Pointwise Maximal Leakage on General Alphabets

200 papers

The study of leakage measures for privacy has been a subject of intensive research and is an important aspect of understanding how privacy leaks occur in computer systems. Differential privacy has been a focal point in the privacy community…

Information Theory · Computer Science 2023-05-19 Natasha Fernandes , Annabelle McIver , Parastoo Sadeghi

This paper considers the problem of estimating the information leakage of a system in the black-box scenario. It is assumed that the system's internals are unknown to the learner, or anyway too complicated to analyze, and the only available…

Cryptography and Security · Computer Science 2021-11-29 Marco Romanelli , Konstantinos Chatzikokolakis , Catuscia Palamidessi , Pablo Piantanida

The choice of free parameters in network models is subjective, since it depends on what topological properties are being monitored. However, we show that the Maximum Likelihood (ML) principle indicates a unique, statistically rigorous…

Disordered Systems and Neural Networks · Physics 2008-08-07 Diego Garlaschelli , Maria I. Loffredo

This paper presents a novel approach to evaluating the security of large language models (LLMs) against prompt leakage-the exposure of system-level prompts or proprietary configurations. We define prompt leakage as a critical threat to…

Cryptography and Security · Computer Science 2025-02-19 Tvrtko Sternak , Davor Runje , Dorian Granoša , Chi Wang

Most methods for publishing data with privacy guarantees introduce randomness into datasets which reduces the utility of the published data. In this paper, we study the privacy-utility tradeoff by taking maximal leakage as the privacy…

Information Theory · Computer Science 2021-05-04 Sara Saeidian , Giulia Cervia , Tobias J. Oechtering , Mikael Skoglund

Large Language Models (LLMs) enable a new ecosystem with many downstream applications, called LLM applications, with different natural language processing tasks. The functionality and performance of an LLM application highly depend on its…

Cryptography and Security · Computer Science 2025-06-16 Bo Hui , Haolin Yuan , Neil Gong , Philippe Burlina , Yinzhi Cao

Language models (LMs) rely on their parametric knowledge augmented with relevant contextual knowledge for certain tasks, such as question answering. However, the contextual knowledge can contain private information that may be leaked when…

Computation and Language · Computer Science 2025-12-17 James Flemings , Bo Jiang , Wanrong Zhang , Zafar Takhirov , Murali Annavaram

This work investigates the problem of analyzing privacy of abrupt changes for general Markov processes. These processes may be affected by changes, or exogenous signals, that need to remain private. Privacy refers to the disclosure of…

Systems and Control · Electrical Eng. & Systems 2021-10-04 Alessio Russo , Alexandre Proutiere

The widespread availability of large-scale code datasets has fueled the rapid development of large language models (LLMs) for code-related tasks. These datasets may include sensitive personally identifiable information (PII), which can lead…

Software Engineering · Computer Science 2026-05-18 Yifei Ge , Zhenpeng Chen , Weisong Sun , Yuchen Chen , Chunrong Fang , Juan Zhai , Xiaofang Zhang , Xia Feng , Yang Liu , Zhenyu Chen

The wide adoption and application of Masked language models~(MLMs) on sensitive data (from legal to medical) necessitates a thorough quantitative investigation into their privacy vulnerabilities -- to what extent do MLMs leak information…

Machine Learning · Computer Science 2022-11-07 Fatemehsadat Mireshghallah , Kartik Goyal , Archit Uniyal , Taylor Berg-Kirkpatrick , Reza Shokri

We study an information-theoretic privacy mechanism design problem, where an agent observes useful data $Y$ that is arbitrarily correlated with sensitive data $X$, and design disclosed data $U$ generated from $Y$ (the agent has no direct…

Information Theory · Computer Science 2026-01-13 Amirreza Zamani , Sajad Daei , Parastoo Sadeghi , Mikael Skoglund

Quantitative information flow (QIF) is concerned with measuring how much of a secret is leaked to an adversary who observes the result of a computation that uses it. Prior work has shown that QIF techniques based on abstract interpretation…

Programming Languages · Computer Science 2018-02-23 Ian Sweet , Jose Manuel Calderon Trilla , Chad Scherrer , Michael Hicks , Stephen Magill

Recently, it has been shown that Machine Learning models can leak sensitive information about their training data. This information leakage is exposed through membership and attribute inference attacks. Although many attack strategies have…

Machine Learning · Computer Science 2023-03-08 Ganesh Del Grosso , Georg Pichler , Catuscia Palamidessi , Pablo Piantanida

Users interacting with large language models (LLMs) under their real identifiers often unknowingly risk disclosing private information. Automatically notifying users whether their queries leak privacy and which phrases leak what private…

Computation and Language · Computer Science 2025-08-11 Hang Zeng , Xiangyu Liu , Yong Hu , Chaoyue Niu , Fan Wu , Shaojie Tang , Guihai Chen

Disclosure of data analytics results has important scientific and commercial justifications. However, no data shall be disclosed without a diligent investigation of risks for privacy of subjects. Privug is a tool-supported method to explore…

Cryptography and Security · Computer Science 2021-08-12 Raúl Pardo , Willard Rafnsson , Christian Probst , Andrzej Wąsowski

The information leakage of a cryptographic implementation with a given degree of protection is evaluated in a typical situation when the signal-to-noise ratio is small. This is solved by expanding Kullback-Leibler divergence, entropy, and…

Information Theory · Computer Science 2021-02-05 Olivier Rioul , Wei Cheng , Sylvain Guilley

Concept Bottleneck Models (CBMs) aim to enhance interpretability by structuring predictions around human-understandable concepts. However, unintended information leakage, where predictive signals bypass the concept bottleneck, compromises…

Machine Learning · Computer Science 2025-07-22 Mikael Makonnen , Moritz Vandenhirtz , Sonia Laguna , Julia E Vogt

Language model (LM) agents that act on users' behalf for personal tasks (e.g., replying emails) can boost productivity, but are also susceptible to unintended privacy leakage risks. We present the first study on people's capacity to oversee…

Human-Computer Interaction · Computer Science 2025-10-07 Zhiping Zhang , Bingcan Guo , Tianshi Li

Process mining employs event data extracted from different types of information systems to discover and analyze actual processes. Event data often contain highly sensitive information about the people who carry out activities or the people…

Cryptography and Security · Computer Science 2022-09-30 Majid Rafiei , Gamal Elkoumy , Wil M. P. van der Aalst

In-Context Learning (ICL) has become a standard technique for adapting Large Language Models (LLMs) to specialized tasks by supplying task-specific exemplars within the prompt. However, when these exemplars contain sensitive information,…

Cryptography and Security · Computer Science 2026-04-22 Jacob Choi , Shuying Cao , Xingjian Dong , Amin Banayeeanzade , Wang Bill Zhu , Robin Jia , Sai Praneeth Karimireddy
‹ Prev 1 3 4 5 6 7 10 Next ›