Related papers: Graded Modal Types for Integrity and Confidentiali…

This paper primarily addresses the issue of identifying all possible levels of digital anonymity, thereby allowing electronic services and mechanisms to be categorised. For this purpose, we sophisticate the generic idea of anonymity and,…

Many properties of communication protocols combine safety and liveness aspects. Characterizing such combined properties by means of a single inference system is difficult because of the fundamentally different techniques (coinduction and…

Large Language Models (LLMs) face threats from jailbreak prompts. Existing methods for detecting jailbreak prompts are primarily online moderation APIs or finetuned LLMs. These strategies, however, often require extensive and…

We present a novel formal system for proving quantitative-leakage properties of programs. Based on a theory of Quantitative Information Flow (QIF) that models information leakage as a noisy communication channel, it uses "gain-functions"…

To prevent concurrency errors, programmers need to obey a locking discipline. Annotations that specify that discipline, such as Java's @GuardedBy, are already widely used. Unfortunately, their semantics is expressed informally and is…

We present several novel identities and inequalities relating the mutual information and the directed information in systems with feedback. The internal blocks within such systems are restricted only to be causal mappings, but are allowed…

The idea of federated learning is to collaboratively train a neural network on a server. Each user receives the current weights of the network and in turns sends parameter updates (gradients) based on local data. This protocol has been…

Mechanism design is the study of algorithm design in which the inputs to the algorithm are controlled by strategic agents, who must be incentivized to faithfully report them. Unlike typical programmatic properties, it is not sufficient for…

Federated learning has emerged as a prominent privacy-preserving technique for leveraging large-scale distributed datasets by sharing gradients instead of raw data. However, recent studies indicate that private training data can still be…

Deep learning models have been extensively adopted in various regions due to their ability to represent hierarchical features, which highly rely on the training set and procedures. Thus, protecting the training process and deep learning…

A fundamental question in natural language processing is - what kind of language structure and semantics is the language model capturing? Graph formats such as knowledge graphs are easy to evaluate as they explicitly express language…

Exchanging mutable data objects with untrusted code is a delicate matter because of the risk of creating a data space that is accessible by an attacker. Consequently, secure programming guidelines for Java stress the importance of using…

Instruction tuning has proven effective in enhancing Large Language Models' (LLMs) performance on downstream tasks. However, real-world fine-tuning faces inherent conflicts between model providers' intellectual property protection, clients'…

As machine learning becomes a more mainstream technology, the objective for governments and public sectors is to harness the power of machine learning to advance their mission by revolutionizing public services. Motivational government use…

To enable process analysis based on an event log without compromising the privacy of individuals involved in process execution, a log may be anonymized. Such anonymization strives to transform a log so that it satisfies provable privacy…

Benefits of static type systems are well-known: they offer guarantees that no type error will occur during runtime and, inherently, inferred types serve as documentation on how functions are called. On the other hand, many type systems have…

We present efficient and practical algorithms for a large, distributed system of processors to achieve reliable computations in a secure manner. Specifically, we address the problem of computing a general function of several private inputs…

Differential privacy is the standard method for privacy-preserving data analysis. The importance of having strong guarantees on the reliability of implementations of differentially private algorithms is widely recognized and has sparked…

Insider threat is one of the most pernicious threat vectors to information and communication technologies (ICT)across the world due to the elevated level of trust and access that an insider is afforded. This type of threat can stem from…

Federated learning has been proposed as a privacy-preserving machine learning framework that enables multiple clients to collaborate without sharing raw data. However, client privacy protection is not guaranteed by design in this framework.…