Related papers: AISafetyLab: A Comprehensive Framework for AI Safe…
Tool-augmented AI agents substantially extend the practical capabilities of large language models, but they also introduce security risks that cannot be identified through model-only evaluation. In this paper, we present a systematic…
Prominent AI experts have suggested that companies developing high-risk AI systems should be required to show that such systems are safe before they can be developed or deployed. The goal of this paper is to expand on this idea and explore…
Although AI systems have been applied in various fields and achieved impressive performance, their safety and reliability are still a big concern. This is especially important for safety-critical tasks. One shared characteristic of these…
The deployment of AI systems faces three critical governance challenges that current frameworks fail to adequately address. First, organizations struggle with inadequate risk assessment at the use case level, exemplified by the Humana class…
This paper proposes a novel framework for developing safe Artificial General Intelligence (AGI) by combining Active Inference principles with Large Language Models (LLMs). We argue that traditional approaches to AI safety, focused on…
As AI systems become increasingly powerful, the need for safe AI has become more pressing. Humans are an attractive model for AI safety: as the only known agents capable of general intelligence, they perform robustly even under conditions…
As AI systems integrate into critical infrastructure, security gaps in AI compliance frameworks demand urgent attention. This paper audits and quantifies security risks in three major AI governance standards: NIST AI RMF 1.0, UK's AI and…
The complex and evolving threat landscape of frontier AI development requires a multi-layered approach to risk management ("defense-in-depth"). By reviewing cybersecurity and AI frameworks, we outline three approaches that can help identify…
This paper maps Africa's distinctive AI risk profile, from deepfake fuelled electoral interference and data colonial dependency to compute scarcity, labour disruption and disproportionate exposure to climate driven environmental costs.…
The integration of Artificial Intelligence in the development of computer systems presents a new challenge: make intelligent systems explainable to humans. This is especially vital in the field of health and well-being, where transparency…
As AI systems become integral to critical operations across industries and services, ensuring their reliability and safety is essential. We offer a framework that integrates established reliability and resilience engineering principles into…
With Artificial intelligence (AI) to aid or automate decision-making advancing rapidly, a particular concern is its fairness. In order to create reliable, safe and trustworthy systems through human-centred artificial intelligence (HCAI)…
Not too long ago, AI security used to mean the research and practice of how AI can empower cybersecurity, that is, AI for security. Ever since Ian Goodfellow and his team popularized adversarial attacks on machine learning, security for AI…
AI models are increasingly prevalent in high-stakes environments, necessitating thorough assessment of their capabilities and risks. Benchmarks are popular for measuring these attributes and for comparing model performance, tracking…
The advancement of artificial intelligence (AI) hinges on the quality and accessibility of data, yet the current fragmentation and variability of data sources hinder efficient data utilization. The dispersion of data sources and diversity…
AI-for-Code (AI4Code) systems are reshaping software engineering, with tools like GitHub Copilot accelerating code generation, translation, and vulnerability detection. Alongside these advances, however, security risks remain pervasive:…
Context: AI code generators are revolutionizing code writing and software development, but their training on large datasets, including potentially untrusted source code, raises security concerns. Furthermore, these generators can produce…
Artificial Intelligence (AI) is becoming the corner stone of many systems used in our daily lives such as autonomous vehicles, healthcare systems, and unmanned aircraft systems. Machine Learning is a field of AI that enables systems to…
The trustworthiness of AI applications has been the subject of recent research and is also addressed in the EU's recently adopted AI Regulation. The currently emerging foundation models in the field of text, speech and image processing…
Given rapid progress toward advanced AI and risks from frontier AI systems (advanced AI systems pushing the boundaries of the AI capabilities frontier), the creation and implementation of AI governance and regulatory schemes deserves…