相关论文: Quantifying Automation Risk in High-Automation AI …
Because human preferences are too complex to codify, AIs operate with misspecified objectives. Optimizing such objectives often produces undesirable outcomes; this phenomenon is known as reward hacking. Such outcomes are not necessarily…
We develop a structural default model for interconnected financial institutions in a probabilistic framework. For all possible network structures we characterize the joint default distribution of the system using Bayesian network…
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…
Agentic AI systems - capable of goal interpretation, world modeling, planning, tool use, long-horizon operation, and autonomous coordination - introduce distinct control failures not addressed by existing safety frameworks. We identify six…
This paper considers the security investment problem over a network in which the resource owners aim to allocate their constrained security resources to heterogeneous targets strategically. Investing in each target makes it less vulnerable,…
Large language models (LLMs) are increasingly embedded in high-stakes workflows, where failures propagate beyond isolated model errors into systemic breakdowns that can lead to legal exposure, reputational damage, and material financial…
The rapid evolution of generative AI has expanded the breadth of risks associated with AI systems. While various taxonomies and frameworks exist to classify these risks, the lack of interoperability between them creates challenges for…
Edge computing has become one of the key enablers for ultra-reliable and low-latency communications in the industrial Internet of Things in the fifth generation communication systems, and is also a promising technology in the future sixth…
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…
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…
The absolute dominance of Artificial Intelligence (AI) introduces unprecedented societal harms and risks. Existing AI risk assessment models focus on internal compliance, often neglecting diverse stakeholder perspectives and real-world…
Artificial intelligence now decides who receives a loan, who is flagged for criminal investigation, and whether an autonomous vehicle brakes in time. Governments have responded: the EU AI Act, the NIST Risk Management Framework, and the…
Autonomous AI agents powered by large language models are being deployed in production with capabilities including shell execution, file system access, database queries, and multi-party communication. Recent red teaming research…
The pervasive integration of Artificial Intelligence (AI) has introduced complex challenges in the responsibility and accountability in the event of incidents involving AI-enabled systems. The interconnectivity of these systems, ethical…
The rapid adoption of AI systems presents enterprises with a dual challenge: accelerating innovation while ensuring responsible governance. Current AI governance approaches suffer from fragmentation, with risk management frameworks that…
Existing AI agent safety benchmarks focus on generic criminal harm (cybercrime, harassment, weapon synthesis), leaving a systematic blind spot for a distinct and commercially consequential threat category: agents harming their own…
Brought into the public discourse through investigative work by journalists and scholars, awareness of algorithmic harms is at an all-time high. An increasing amount of research has been conducted under the banner of enhancing responsible…
Fault detection has a long tradition: the necessity to provide the most accurate diagnosis possible for a process plant criticality is somehow intrinsic in its functioning. Continuous monitoring is a possible way for early detection.…
The rise of AI has transformed the software and hardware landscape, enabling powerful capabilities through specialized infrastructures, large-scale data storage, and advanced hardware. However, these innovations introduce unique attack…
This chapter introduces the Bayesian reflex -- an analogy with the autonomic nervous system -- as a unifying framework for online learning in AI. Bayesian online algorithms automatically maintain equilibrium in dynamic environments via…