Related papers: The AI Security Zugzwang
The field of AI alignment aims to steer AI systems toward human goals, preferences, and ethical principles. Its contributions have been instrumental for improving the output quality, safety, and trustworthiness of today's AI models. This…
When AI interacts with the physical world -- as a robot or an assistive agent -- new safety challenges emerge beyond those of purely ``digital AI". In such interactions, the potential for physical harm is direct and immediate. How well do…
Edge AI is often framed as model compression and deployment under tight constraints. We argue a stronger operational thesis: Edge AI in realistic deployments is necessarily adaptive. In long-horizon operation, a fixed (non-adaptive)…
This paper argues that AI alignment is not merely difficult, but is founded on a fundamental logical contradiction. We first establish The Enumeration Paradox: we use machine learning precisely because we cannot enumerate all necessary…
AI systems have found a wide range of real-world applications in recent years. The adoption of edge artificial intelligence, embedding AI directly into edge devices, is rapidly growing. Despite the implementation of guardrails and safety…
This paper contributes a new way to evaluate AI. Much as one might evaluate a machine in terms of its performance at chess, this approach involves evaluating a machine in terms of its performance at a game called "MAD Chairs". At the time…
In AI, the existential risk denotes the hypothetical threat posed by an artificial system that would possess both the capability and the objective, either directly or indirectly, to eradicate humanity. This issue is gaining prominence in…
Artificial Intelligence (AI) algorithms are increasingly providing decision making and operational support across multiple domains. AI includes a wide library of algorithms for different problems. One important notion for the adoption of AI…
Agentic AI systems -- Large Language Models (LLMs) augmented with planning, tool use, memory, and long-horizon interactions -- can execute complex tasks autonomously, but their multi-step trajectories introduce new failure modes that…
Technological advances of virtually every kind pose risks to society including fairness and bias. We review a long-standing wisdom that a widespread practical deployment of any technology may produce adverse side effects misusing the…
Amid growing concerns over AI's societal risks--ranging from civilizational collapse to misinformation and systemic bias--this study explores the perceptions of AI experts and the general US registered voters on the likelihood and impact of…
Artificial Intelligence (AI) is one of the disruptive technologies that is shaping the future. It has growing applications for data-driven decisions in major smart city solutions, including transportation, education, healthcare, public…
As AI becomes increasingly embedded in digital games, players' attitudes de-pend not only on whether AI is used, but also on where and how it intervenes in gameplay. This study examines players' evaluative patterns toward eight AI…
Rapidly advancing artificial intelligence (AI) systems introduce novel, uncertain, and potentially catastrophic risks. Managing these risks requires a mature risk-management infrastructure whose cornerstone is rigorous risk modeling. We…
Structured access is an emerging paradigm for the safe deployment of artificial intelligence (AI). Instead of openly disseminating AI systems, developers facilitate controlled, arm's length interactions with their AI systems. The aim is to…
This paper bridges distribution shift and AI safety through a comprehensive analysis of their conceptual and methodological synergies. While prior discussions often focus on narrow cases or informal analogies, we establish two types…
Sociotechnical requirements shape the governance of artificially intelligent (AI) systems. In an era where embodied AI technologies are rapidly reshaping various facets of contemporary society, their inherent dynamic adaptability presents a…
We have convinced ourselves that the way to make AI safe is to make it unsafe. Since 2022, policymakers worldwide have embraced the Regulation Sacrifice - the belief that dismantling safety oversight will deliver security through AI…
The key problem facing ChatGPT-like AI's use across society is that its behavior can shift, unnoticed, from desirable to undesirable -- encouraging self-harm, extremist acts, financial losses, or costly medical and military mistakes -- and…
Tool-enabled AI agents are increasingly deployed in cloud-hosted environments and offered as services, where they perform side-effecting operations through privileged tools within execution environments. While such agents enable powerful…