相关论文: Adapting Probabilistic Risk Assessment for AI

The use of AI technologies is being integrated into the secure development of software-based systems, with an increasing trend of composing AI-based subsystems (with uncertain levels of performance) into automated pipelines. This presents a…

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…

The prevailing methodologies for visualizing AI risks have focused on technical issues such as data biases and model inaccuracies, often overlooking broader societal risks like job loss and surveillance. Moreover, these visualizations are…

Researchers, government bodies, and organizations have been repeatedly calling for a shift in the responsible AI community from general principles to tangible and operationalizable practices in mitigating the potential sociotechnical harms…

Artificial intelligence (AI) is being ubiquitously adopted to automate processes in science and industry. However, due to its often intricate and opaque nature, AI has been shown to possess inherent vulnerabilities which can be maliciously…

Recent developments in artificial intelligence (AI) have permeated through an array of different immersive environments, including virtual, augmented, and mixed realities. AI brings a wealth of potential that centers on its ability to…

Artificial intelligence commonly refers to the science and engineering of artificial systems that can carry out tasks generally associated with requiring aspects of human intelligence, such as playing games, translating languages, and…

The introduction of the European Union Artificial Intelligence Act, the NIST Artificial Intelligence Risk Management Framework, and related norms demands a better understanding and implementation of novel risk analysis approaches to…

The modern pervasiveness of large-scale deep neural networks (NNs) is driven by their extraordinary performance on complex problems but is also plagued by their sudden, unexpected, and often catastrophic failures, particularly on…

Scientific research organizations that are developing and deploying Artificial Intelligence (AI) systems are at the intersection of technological progress and ethical considerations. The push for Responsible AI (RAI) in such institutions…

Artificial intelligence systems are now deployed at scale across sectors, accompanied by a growing number of real-world incidents ranging from misinformation and cybercrime to autonomous-system failures. Databases of AI incidents index…

Risk assessments for advanced AI systems require evaluating both the models themselves and their deployment contexts. We introduce the Societal Capacity Assessment Framework (SCAF), an indicators-based approach to measuring a society's…

In safety-critical deep learning applications robustness measurement is a vital pre-deployment phase. However, existing robustness verification methods are not sufficiently practical for deploying machine learning systems in the real world.…

A global challenge in artificial intelligence (AI) regulation lies in achieving effective risk management without compromising innovation and technical progress. The European Union (EU) Artificial Intelligence Act represents the first…

The rapid proliferation of artificial intelligence (AI) has exposed significant deficiencies in risk governance. While ex-ante harm identification and prevention have advanced, Responsible AI scholarship remains underdeveloped in addressing…

Responsible Artificial Intelligence (RAI) addresses the ethical and regulatory challenges of deploying AI systems in high-risk scenarios. This paper proposes a comprehensive framework for the design of an RAI system (RAIS) that integrates…

Quantum Artificial Intelligence (QAI), the integration of Artificial Intelligence (AI) and Quantum Computing (QC), promises transformative advances, including AI-enabled quantum cryptography and quantum-resistant encryption protocols.…

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…

A comprehensive approach to addressing catastrophic risks from AI models should cover the full model lifecycle. This paper explores contingency plans for cases where pre-deployment risk management falls short: where either very dangerous…

Estimating catastrophic harms from frontier AI is hindered by deep ambiguity: many of its risks are not only unobserved but unanticipated by analysts. The central limitation of current risk analysis is the inability to populate the…