Related papers: Securing External Deeper-than-black-box GPAI Evalu…
Artificial intelligence (AI) technologies (re-)shape modern life, driving innovation in a wide range of sectors. However, some AI systems have yielded unexpected or undesirable outcomes or have been used in questionable manners. As a…
To understand the risks posed by a new AI system, we must understand what it can and cannot do. Building on prior work, we introduce a programme of new "dangerous capability" evaluations and pilot them on Gemini 1.0 models. Our evaluations…
Artificial Intelligence (AI) is an important part of our everyday lives. We use it in self-driving cars and smartphone assistants. People often call it a "black box" because its complex systems, especially deep neural networks, are hard to…
The performance of AI models on safety benchmarks does not indicate their real-world performance after deployment. This opaqueness of AI models impedes existing regulatory frameworks constituted on benchmark performance, leaving them…
As artificial intelligence plays an increasingly important role in our society, there are ethical and moral obligations for both businesses and researchers to ensure that their machine learning models are designed, deployed, and maintained…
Advanced AI models hold the promise of tremendous benefits for humanity, but society needs to proactively manage the accompanying risks. In this paper, we focus on what we term "frontier AI" models: highly capable foundation models that…
We review practical challenges in building and deploying ethical AI at the scale of contemporary industrial and societal uses. Apart from the purely technical concerns that are the usual focus of academic research, the operational…
In this work, we provide an industry research view for approaching the design, deployment, and operation of trustworthy Artificial Intelligence (AI) inference systems. Such systems provide customers with timely, informed, and customized…
Deep neural networks are becoming popular and important assets of many AI companies. However, recent studies indicate that they are also vulnerable to adversarial attacks. Adversarial attacks can be either white-box or black-box. The…
To facilitate the widespread acceptance of AI systems guiding decision-making in real-world applications, it is key that solutions comprise trustworthy, integrated human-AI systems. Not only in safety-critical applications such as…
Recent progress in artificial intelligence (AI) using deep learning techniques has triggered its wide-scale use across a broad range of applications. These systems can already perform tasks such as natural language processing of voice and…
Benefiting from the rapid development of deep learning, 2D and 3D computer vision applications are deployed in many safe-critical systems, such as autopilot and identity authentication. However, deep learning models are not trustworthy…
In the past few years, artificial intelligence (AI) techniques have been implemented in almost all verticals of human life. However, the results generated from the AI models often lag explainability. AI models often appear as a blackbox…
At the current pace of technological advancements, Generative AI models, including both Large Language Models and Large Multi-modal Models, are becoming integral to the developer workspace. However, challenges emerge due to the 'black box'…
Estimating the probability of failure is an important step in the certification of safety-critical systems. Efficient estimation methods are often needed due to the challenges posed by high-dimensional input spaces, risky test scenarios,…
Ensuring both transparency and safety is critical when deploying Deep Neural Networks (DNNs) in high-risk applications, such as medicine. The field of explainable AI (XAI) has proposed various methods to comprehend the decision-making…
We draw on our experience working on system and software assurance and evaluation for systems important to society to summarise how safety engineering is performed in traditional critical systems, such as aircraft flight control. We analyse…
As AI models are increasingly deployed across diverse real-world scenarios, ensuring their safety remains a critical yet underexplored challenge. While substantial efforts have been made to evaluate and enhance AI safety, the lack of a…
The success of artificial intelligence (AI), and deep learning models in particular, has led to their widespread adoption across various industries due to their ability to process huge amounts of data and learn complex patterns. However,…
Across academia, industry, and government, there is an increasing awareness that the measurement tasks involved in evaluating generative AI (GenAI) systems are especially difficult. We argue that these measurement tasks are highly…