Related papers: Security Incentivization: An Empirical Study of ho…
In order for agents trained by deep reinforcement learning to work alongside humans in realistic settings, we will need to ensure that the agents are \emph{robust}. Since the real world is very diverse, and human behavior often changes in…
We propose a comparative performance evaluation of security protocols. The novelty of our approach lies in the use of a polynomial mathematical model that captures the performance of classes of cryptographic algorithms instead of capturing…
Background: Timely prioritising and remediating vulnerabilities are paramount in the dynamic cybersecurity field, and one of the most widely used vulnerability scoring systems (CVSS) does not address the increasing likelihood of emerging an…
Cryptocurrencies have gained popularity due to their transparency, security, and accessibility compared to traditional financial systems, with Bitcoin, introduced in 2009, leading the market. Bitcoin's security relies on blockchain…
Secure multi-party computation has seen substantial performance improvements in recent years and is being increasingly used in commercial products. While a significant amount of work was dedicated to improving its efficiency under standard…
The rise of model sharing through frameworks and dedicated hubs makes Machine Learning significantly more accessible. Despite its benefits, loading shared models exposes users to underexplored security risks, while security awareness…
Future AI deployments will likely be monitored for malicious behaviour. The ability of these AIs to subvert monitors by adversarially selecting against them - attack selection - is particularly concerning. To study this, we let a red team…
Cybersecurity practices require effort to be maintained, and one weakness is a lack of awareness regarding potential attacks not only in the usage of machine learning models, but also in their development process. Previous studies have…
In this paper, we ask the question of why the quality of commercial software, in terms of security and safety, does not measure up to that of other (durable) consumer goods we have come to expect. We examine this question through the lens…
Evaluating the effectiveness of software protection is crucial for selecting the most effective methods to safeguard assets within software applications. Obfuscation involves techniques that deliberately modify software to make it more…
Code-generating Artificial Intelligence has gained popularity within both professional and educational programming settings over the past several years. While research and pedagogy are beginning to cope with this change, computing students…
Reinforcement Learning (RL) has achieved remarkable success in safety-critical areas, but it can be weakened by adversarial attacks. Recent studies have introduced "smoothed policies" in order to enhance its robustness. Yet, it is still…
LLM agents are increasingly relevant to research domains such as vulnerability discovery. Yet, the strongest systems remain closed and cloud-only, making them resource-intensive, difficult to reproduce, and unsuitable for work involving…
How should we decide which fairness criteria or definitions to adopt in machine learning systems? To answer this question, we must study the fairness preferences of actual users of machine learning systems. Stringent parity constraints on…
Hands-on cybersecurity training allows students and professionals to practice various tools and improve their technical skills. The training occurs in an interactive learning environment that enables completing sophisticated tasks in…
Restaking protocols have aggregated billions of dollars of security by utilizing token incentives and payments. A natural question to ask is: How much security do restaked services \emph{really} need to purchase? To answer this question, we…
Software bots have been facilitating several development activities in Open Source Software (OSS) projects, including code review. However, these bots may bring unexpected impacts to group dynamics, as frequently occurs with new technology…
Training next-generation code generation models requires high-quality datasets, yet existing datasets face difficulty imbalance, format inconsistency, and data quality problems. We address these challenges through systematic data processing…
Large Language Models (LLMs) are increasingly integrated into high-stakes applications, making robust safety guarantees a central practical and commercial concern. Existing safety evaluations predominantly rely on fixed collections of…
In code comprehension experiments, participants are usually told at the beginning what kind of code comprehension task to expect. Describing experiment scenarios and experimental tasks will influence participants in ways that are sometimes…