English
Related papers

Related papers: Honesty by Typing

200 papers

STEALTH is a method for using some AI-generated model, without suffering from malicious attacks (i.e. lying) or associated unfairness issues. After recursively bi-clustering the data, STEALTH system asks the AI model a limited number of…

Software Engineering · Computer Science 2023-01-26 Lauren Alvarez , Tim Menzies

Transparency is an essential requirement of machine learning based decision making systems that are deployed in real world. Often, transparency of a given system is achieved by providing explanations of the behavior and predictions of the…

Machine Learning · Computer Science 2021-05-18 André Artelt , Barbara Hammer

We propose a protocol based on mechanism design theory and encrypted control to solve average consensus problems among rational and strategic agents while preserving their privacy. The proposed protocol provides a mechanism that…

Systems and Control · Electrical Eng. & Systems 2025-08-27 Kaoru Teranishi , Kiminao Kogiso , Takashi Tanaka

We present a type theory combining both linearity and dependency by stratifying typing rules into a level for logics and a level for programs. The distinction between logics and programs decouples their semantics, allowing the type system…

Programming Languages · Computer Science 2025-10-08 Qiancheng Fu , Hongwei Xi

This paper describes a method for creating compelling safety cases. The method seeks to help improve safety case practice in order to address the weaknesses identified in current practice, in particular confirmation bias, after-the-fact…

Software Engineering · Computer Science 2025-02-04 Richard Hawkins

Smart contract applications on the blockchain can only reach their full potential if they integrate seamlessly with traditional software systems via a programmatic interface. This interface should provide for originating and invoking…

Programming Languages · Computer Science 2021-08-31 Thi Thu Ha Doan , Peter Thiemann

In this paper we present the probabilistic typed natural deduction calculus TPTND, designed to reason about and derive trustworthiness properties of probabilistic computational processes, like those underlying current AI applications.…

Logic in Computer Science · Computer Science 2025-02-14 Fabio Aurelio D'Asaro , Francesco Genco , Giuseppe Primiero

Web Service is one of the most important information sharing technologies on the web and one of the example of service oriented processing. To guarantee accurate execution of web services operations, they must be accountable with…

Social and Information Networks · Computer Science 2014-12-12 Marzieh Adelnia , Mohammad Reza Khayyambashi

We tackle the problem of statically ensuring that message-passing programs never run into deadlocks. We focus on concurrent functional programs governed by context-free session types, which can express rich tree-like structures not…

Programming Languages · Computer Science 2026-02-24 Andreia Mordido , Jorge A. Pérez

Smart contracts are crucial elements of decentralized technologies, but they face significant obstacles to trustworthiness due to security bugs and trapdoors. To address the core issue, we propose a technology that enables programmers to…

Cryptography and Security · Computer Science 2023-04-19 Nikolaj Bjørner , Shuo Chen , Yang Chen , Zhongxin Guo , Peng Liu , Nanqing Luo

We introduce a new two-sided type system for verifying the correctness and incorrectness of functional programs with atoms and pattern matching. A key idea in the work is that types should range over sets of normal forms, rather than sets…

Programming Languages · Computer Science 2026-05-11 Celia Mengyue Li , Sophie Pull , Steven Ramsay

We propose a smart contract that allows two mutually distrusting parties to transact any non-digital good or service by deploying a smart contract on a blockchain to act as escrow. The contract settles disputes by letting parties wager that…

Computer Science and Game Theory · Computer Science 2023-04-05 Nikolaj Ignatieff Schwartzbach

Humans can generate reasonable answers to novel queries (Schulz, 2012): if I asked you what kind of food you want to eat for lunch, you would respond with a food, not a time. The thought that one would respond "After 4pm" to "What would you…

Artificial Intelligence · Computer Science 2022-10-05 Felix A. Sosa , Tomer Ullman

In the paper we introduce a process model of security protocols, where processes are graphs with edges labelled by actions, and present a new method of specification and verification of security protocols based on this model.

Logic in Computer Science · Computer Science 2017-06-02 Andrew M. Mironov

Accountability aims to provide explanations for why unwanted situations occurred, thus providing means to assign responsibility and liability. As such, accountability has slightly different meanings across the sciences. In computer science,…

Computers and Society · Computer Science 2016-08-30 Severin Kacianka , Florian Kelbert , Alexander Pretschner

The notion of subtyping has gained an important role both in theoretical and applicative domains: in lambda and concurrent calculi as well as in programming languages. The soundness and the completeness, together referred to as the…

Logic in Computer Science · Computer Science 2016-02-12 Mariangiola Dezani-Ciancaglini , Silvia Ghilezan , Svetlana Jakšić , Jovanka Pantović , Nobuko Yoshida

How much are we to trust a decision made by an AI algorithm? Trusting an algorithm without cause may lead to abuse, and mistrusting it may similarly lead to disuse. Trust in an AI is only desirable if it is warranted; thus, calibrating…

Human-Computer Interaction · Computer Science 2023-03-27 Neil Natarajan , Reuben Binns , Jun Zhao , Nigel Shadbolt

The emergence of pre-trained AI systems with powerful capabilities across a diverse and ever-increasing set of complex domains has raised a critical challenge for AI safety as tasks can become too complicated for humans to judge directly.…

Artificial Intelligence · Computer Science 2023-11-27 Jonah Brown-Cohen , Geoffrey Irving , Georgios Piliouras

The Message Passing Interface (MPI) framework is widely used in implementing imperative pro- grams that exhibit a high degree of parallelism. The PARTYPES approach proposes a behavioural type discipline for MPI-like programs in which a type…

Programming Languages · Computer Science 2017-04-12 Francisco Martins , Vasco Thudichum Vasconcelos , Hans Hüttel

Testing of network services represents one of the biggest challenges in cyber security. Because new vulnerabilities are detected on a regular basis, more research is needed. These faults have their roots in the software development cycle or…

Cryptography and Security · Computer Science 2018-03-29 Josip Bozic , Lina Marsso , Radu Mateescu , Franz Wotawa