Related papers: Evaluating Nova 2.0 Lite model under Amazon's Fron…
Nova Premier is Amazon's most capable multimodal foundation model and teacher for model distillation. It processes text, images, and video with a one-million-token context window, enabling analysis of large codebases, 400-page documents,…
We present Amazon Nova, a new generation of state-of-the-art foundation models that deliver frontier intelligence and industry-leading price performance. Amazon Nova Pro is a highly-capable multimodal model with the best combination of…
As part of the Frontier AI Safety Commitments agreed to at the 2024 AI Seoul Summit, many AI developers agreed to publish a safety framework outlining how they will manage potential severe risks associated with their systems. This paper…
To understand and identify the unprecedented risks posed by rapidly advancing artificial intelligence (AI) models, Frontier AI Risk Management Framework in Practice presents a comprehensive assessment of their frontier risks. As Large…
Powerful new frontier AI technologies are bringing many benefits to society but at the same time bring new risks. AI developers and regulators are therefore seeking ways to assure the safety of such systems, and one promising method under…
Following the AI Seoul Summit in 2024, twelve AI companies published frontier AI safety frameworks (Frameworks) outlining their approaches to managing catastrophic risks from advanced AI systems. Emerging legislation increasingly treats…
To understand and identify the unprecedented risks posed by rapidly advancing artificial intelligence (AI) models, this report presents a comprehensive assessment of their frontier risks. Drawing on the E-T-C analysis (deployment…
Rapidly evolving AI exhibits increasingly strong autonomy and goal-directed capabilities, accompanied by derivative systemic risks that are more unpredictable, difficult to control, and potentially irreversible. However, current AI safety…
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…
Neural networks are increasingly deployed in real-world safety-critical domains such as autonomous driving, aircraft collision avoidance, and malware detection. However, these networks have been shown to often mispredict on inputs with…
The rapid advancement of large models, driven by their exceptional abilities in learning and generalization through large-scale pre-training, has reshaped the landscape of Artificial Intelligence (AI). These models are now foundational to a…
The rapid advancement of large language models (LLMs) introduces dual-use capabilities that could both threaten and bolster national security and public safety (NSPS). Models implement safeguards to protect against potential misuse relevant…
The recent development of powerful AI systems has highlighted the need for robust risk management frameworks in the AI industry. Although companies have begun to implement safety frameworks, current approaches often lack the systematic…
Adversarial attacks for machine learning models have become a highly studied topic both in academia and industry. These attacks, along with traditional security threats, can compromise confidentiality, integrity, and availability of…
As generative AI systems, including large language models (LLMs) and diffusion models, advance rapidly, their growing adoption has led to new and complex security risks often overlooked in traditional AI risk assessment frameworks. This…
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…
Artificial intelligence (AI) systems can provide many beneficial capabilities but also risks of adverse events. Some AI systems could present risks of events with very high or catastrophic consequences at societal scale. The US National…
This study offers an in-depth analysis of the application and implications of the National Institute of Standards and Technology's AI Risk Management Framework (NIST AI RMF) within the domain of surveillance technologies, particularly…
Machine learning (ML) models are used in many safety- and security-critical applications nowadays. It is therefore important to measure the security of a system that uses ML as a component. This paper focuses on the field of ML,…
AI has become integral to safety-critical areas like autonomous driving systems (ADS) and robotics. The architecture of recent autonomous systems are trending toward end-to-end (E2E) monolithic architectures such as large language models…