Related papers: Pre-Deployment Information Sharing: A Zoning Taxon…

As machine learning models become increasingly deployed across the edge of internet of things environments, a partitioned deep learning paradigm in which models are split across multiple computational nodes introduces a new dimension of…

This paper explores the role and challenges of Artificial Intelligence (AI) algorithms, specifically AI-based software elements, in autonomous driving systems. These AI systems are fundamental in executing real-time critical functions in…

Artificial intelligence (AI) is increasingly being used to augment and automate cyber operations, altering the scale, speed, and accessibility of malicious activity. These shifts raise urgent questions about when AI systems introduce…

The governance of frontier AI increasingly relies on controlling access to computational resources, yet the hardware-level mechanisms invoked by policy proposals remain largely unexamined from an engineering perspective. This paper bridges…

Three closely-related polynomial-based group key pre-distribution schemes have recently been proposed, aimed specifically at wireless sensor networks. The schemes enable any subset of a predefined set of sensor nodes to establish a shared…

Interference is traditionally viewed as a performance limiting factor in wireless communication systems, which is to be minimized or mitigated. Nevertheless, a recent line of work has shown that by manipulating the interfering signals such…

As coding agents gain access to shells, repositories, and user files, least-privilege authorization becomes a prerequisite for safe deployment: an agent should receive enough authority to complete the task, without unnecessary authority…

For the safe sharing pre-trained language models, no guidelines exist at present owing to the difficulty in estimating the upper bound of the risk of privacy leakage. One problem is that previous studies have assessed the risk for different…

Deep neural networks provide state-of-the-art accuracy for vision tasks but they require significant resources for training. Thus, they are trained on cloud servers far from the edge devices that acquire the data. This issue increases…

The rapid advancement of artificial intelligence (AI) technologies presents profound challenges to societal safety. As AI systems become more capable, accessible, and integrated into critical services, the dual nature of their potential is…

As AI systems become more capable, integrated, and widespread, understanding the associated risks becomes increasingly important. This paper maps the full spectrum of AI risks, from current harms affecting individual users to existential…

Compute governance proposals often rely on the assumption that frontier AI training requires large, detectable computing clusters. However, recent advances in distributed training algorithms could allow developers to conduct frontier-scale…

Prompt injection is the most critical vulnerability in deployed AI agents. Despite recent progress, we show that the prevailing defense paradigm (data-instruction separation) both fails to detect attacks that operate through contextual…

There is a rising interest in using artificial intelligence (AI)-powered safety analytics to predict accidents in the trucking industry. Companies may face the practical challenge, however, of not having enough data to develop good safety…

For mixed-initiative control between cyber-physical systems (CPS) and its users, it is still an open question how machines can safely hand over control to humans. In this work, we propose a concept to provide technological support that uses…

The steady increase in the volume of indicators of compromise (IoC) as well as their volatile nature makes their processing challenging. Once compromised infrastructures are cleaned up, threat actors are moving to on to other target…

Since the publication of the first International AI Safety Report, AI capabilities have continued to improve across key domains. New training techniques that teach AI systems to reason step-by-step and inference-time enhancements have…

Current approaches to AI safety define red lines at the case level: specific prompts, specific outputs, specific harms. This paper argues that red lines can be set more fundamentally -- at the level of value, evidence, and source…

The ubiquity of social platforms has reshaped the way information, behaviors, and advertisements diffuse across networks, with influence propagation often initiated by a small set of ``seed'' users. While much of the literature emphasizes…

As artificial intelligence (AI) becomes integral to economy and society, communication gaps between developers, users, and stakeholders hinder trust and informed decision-making. High-level AI labels, inspired by frameworks like EU energy…