English
Related papers

Related papers: Learning Character Strings via Mastermind Queries,…

200 papers

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

In a biometric authentication or identification system, the matcher compares a stored and a fresh template to determine whether there is a match. This assessment is based on both a similarity score and a predefined threshold. For better…

Cryptography and Security · Computer Science 2024-07-31 Axel Durbet , Kevin Thiry-Atighehchi , Dorine Chagnon , Paul-Marie Grollemund

Large Language Models for Code (LLMs4Code) have achieved strong performance in code generation, but recent studies reveal that they may memorize and leak sensitive information contained in training data, posing serious privacy risks. To…

Cryptography and Security · Computer Science 2026-01-29 Shanzhi Gu , Zhaoyang Qu , Ruotong Geng , Mingyang Geng , Shangwen Wang , Chuanfu Xu , Haotian Wang , Zhipeng Lin , Dezun Dong

Language Models (LMs) have been shown to leak information about training data through sentence-level membership inference and reconstruction attacks. Understanding the risk of LMs leaking Personally Identifiable Information (PII) has…

Machine Learning · Computer Science 2023-04-25 Nils Lukas , Ahmed Salem , Robert Sim , Shruti Tople , Lukas Wutschitz , Santiago Zanella-Béguelin

We suggest that the randomness of the choices of measurement basis by Alice and Bob provides an additional important resource for quantum cryptography. As a specific application, we present a novel protocol for quantum key distribution…

Quantum Physics · Physics 2016-08-16 Hannes R. Böhm , Paul S. Böhm , Markus Aspelmeyer , Časlav Brukner , Anton Zeilinger

In the inference attacks studied in Quantitative Information Flow (QIF), the attacker typically tries to interfere with the system in the attempt to increase its leakage of secret information. The defender, on the other hand, typically…

Cryptography and Security · Computer Science 2018-05-22 Mário S. Alvim , Konstantinos Chatzikokolakis , Yusuke Kawamoto , Catuscia Palamidessi

Deep neural networks have been demonstrated to be vulnerable to backdoor attacks. Specifically, by injecting a small number of maliciously constructed inputs into the training set, an adversary is able to plant a backdoor into the trained…

Machine Learning · Statistics 2019-12-10 Alexander Turner , Dimitris Tsipras , Aleksander Madry

Training deep neural networks often forces users to work in a distributed or outsourced setting, accompanied with privacy concerns. Split learning aims to address this concern by distributing the model among a client and a server. The…

Cryptography and Security · Computer Science 2022-09-19 Ege Erdogan , Alptekin Kupcu , A. Ercument Cicek

How much does a machine learning algorithm leak about its training data, and why? Membership inference attacks are used as an auditing tool to quantify this leakage. In this paper, we present a comprehensive \textit{hypothesis testing…

Machine Learning · Computer Science 2022-09-14 Jiayuan Ye , Aadyaa Maddi , Sasi Kumar Murakonda , Vincent Bindschaedler , Reza Shokri

Cheat sensitive quantum bit commitment (CSQBC) loosens the security requirement of quantum bit commitment (QBC), so that the existing impossibility proofs of unconditionally secure QBC can be evaded. But here we analyze the common features…

Quantum Physics · Physics 2015-06-09 Guang Ping He

Quantum Key Distribution allows two parties to establish a secret key that is secure against computationally unbounded adversaries. To extend the distance between parties, quantum networks, and in particular repeater chains, are vital.…

Quantum Physics · Physics 2024-06-25 Adrian Harkness , Walter O. Krawec , Bing Wang

Split learning is a promising paradigm for privacy-preserving distributed learning. The learning model can be cut into multiple portions to be collaboratively trained at the participants by exchanging only the intermediate results at the…

Machine Learning · Computer Science 2024-03-25 Junlin Liu , Xinchen Lyu , Qimei Cui , Xiaofeng Tao

We consider the problem of secure identification: user U proves to server S that he knows an agreed (possibly low-entropy) password w, while giving away as little information on w as possible, namely the adversary can exclude at most one…

Quantum Physics · Physics 2009-08-05 Ivan Damgaard , Serge Fehr , Louis Salvail , Christian Schaffner

Secure multi-party machine learning allows several parties to build a model on their pooled data to increase utility while not explicitly sharing data with each other. We show that such multi-party computation can cause leakage of global…

Machine Learning · Computer Science 2021-06-21 Wanrong Zhang , Shruti Tople , Olga Ohrimenko

The use of personal data for training machine learning systems comes with a privacy threat and measuring the level of privacy of a model is one of the major challenges in machine learning today. Identifying training data based on a trained…

Machine Learning · Computer Science 2022-03-24 Ganesh Del Grosso , Hamid Jalalzai , Georg Pichler , Catuscia Palamidessi , Pablo Piantanida

Quantitative Information Flow (QIF) provides a robust information-theoretical framework for designing secure systems with minimal information leakage. While previous research has addressed the design of such systems under hard constraints…

Cryptography and Security · Computer Science 2024-11-18 Andreas Athanasiou , Konstantinos Chatzikokolakis , Catuscia Palamidessi

We study the query complexity of a permutation-based variant of the guessing game Mastermind. In this variant, the secret is a pair $(z,\pi)$ which consists of a binary string $z \in \{0,1\}^n$ and a permutation $\pi$ of $[n]$. The secret…

Data Structures and Algorithms · Computer Science 2018-12-21 Peyman Afshani , Manindra Agrawal , Benjamin Doerr , Carola Doerr , Kasper Green Larsen , Kurt Mehlhorn

Adversarial attacks on machine learning-based classifiers, along with defense mechanisms, have been widely studied in the context of single-label classification problems. In this paper, we shift the attention to multi-label classification,…

Machine Learning · Computer Science 2022-12-07 Stefano Melacci , Gabriele Ciravegna , Angelo Sotgiu , Ambra Demontis , Battista Biggio , Marco Gori , Fabio Roli

We introduce a new type of cryptographic primitive that we call hiding fingerprinting. A (quantum) fingerprinting scheme translates a binary string of length $n$ to $d$ (qu)bits, typically $d\ll n$, such that given any string $y$ and a…

Quantum Physics · Physics 2022-03-30 Dmytro Gavinsky , Tsuyoshi Ito

Standard pretrained language models operate on sequences of subword tokens without direct access to the characters that compose each token's string representation. We probe the embedding layer of pretrained language models and show that…

Computation and Language · Computer Science 2022-06-09 Itay Itzhak , Omer Levy