English
Related papers

Related papers: Out of Control -- Why Alignment Needs Formal Contr…

200 papers

Achieving safe and robust autonomy is the key bottleneck on the path towards broader adoption of autonomous vehicles technology. This motivates going beyond extrinsic metrics such as miles between disengagement, and calls for approaches…

The conversation around artificial intelligence (AI) often focuses on safety, transparency, accountability, alignment, and responsibility. However, AI security (i.e., the safeguarding of data, models, and pipelines from adversarial…

Cryptography and Security · Computer Science 2025-04-24 Krti Tallam

AI deployment in sensitive domains such as health care, credit, employment, and criminal justice is often treated as unsafe to authorize until model internals can be explained. This often leads to an excessive reliance on mechanistic…

Humans strive to design safe AI systems that align with our goals and remain under our control. However, as AI capabilities advance, we face a new challenge: the emergence of deeper, more persistent relationships between humans and AI…

Human-Computer Interaction · Computer Science 2025-02-05 Hannah Rose Kirk , Iason Gabriel , Chris Summerfield , Bertie Vidgen , Scott A. Hale

The inner alignment problem, which asserts whether an arbitrary artificial intelligence (AI) model satisfices a non-trivial alignment function of its outputs given its inputs, is undecidable. This is rigorously proved by Rice's theorem,…

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…

Computers and Society · Computer Science 2024-06-25 Akash R. Wasil , Joshua Clymer , David Krueger , Emily Dardaman , Simeon Campos , Evan R. Murphy

As frontier artificial intelligence (AI) systems become more capable, it becomes more important that developers can explain why their systems are sufficiently safe. One way to do so is via safety cases: reports that make a structured…

Computers and Society · Computer Science 2024-10-30 Marie Davidsen Buhl , Gaurav Sett , Leonie Koessler , Jonas Schuett , Markus Anderljung

This paper leverages insights from Alignment Theory (AT) research, which primarily focuses on the potential pitfalls of technical alignment in Artificial Intelligence, to critically examine the European Union's Artificial Intelligence Act…

Computers and Society · Computer Science 2024-10-29 Alejandro Tlaie

In formation control, an ensemble of autonomous agents is required to stabilize at a given configuration in the plane, doing so while agents are allowed to observe only a subset of the ensemble. As such, formation control provides a rich…

Optimization and Control · Mathematics 2011-10-07 M. -A. Belabbas

Artificial intelligence (AI) is advancing exponentially and is likely to have profound impacts on human wellbeing, social equity, and environmental sustainability. Here we argue that the "alignment problem" in AI research is also an…

General Economics · Economics 2026-04-30 Daniel W. O'Neill , Stefano Vrizzi , Noemi Luna Carmeno , Felix Creutzig , Jefim Vogel

AI safety has emerged as a critical priority as these systems are increasingly deployed in real-world applications. We propose the first domain-agnostic AI safety ensuring framework that achieves strong safety guarantees while preserving…

Artificial Intelligence · Computer Science 2025-10-07 Beomjun Kim , Kangyeon Kim , Sunwoo Kim , Yeonsang Shin , Heejin Ahn

Increasingly, laws are being proposed and passed by governments around the world to regulate Artificial Intelligence (AI) systems implemented into the public and private sectors. Many of these regulations address the transparency of AI…

Computers and Society · Computer Science 2022-07-05 Andrew Bell , Oded Nov , Julia Stoyanovich

This paper introduces Admissibility Alignment: a reframing of AI alignment as a property of admissible action and decision selection over distributions of outcomes under uncertainty, evaluated through the behavior of candidate policies. We…

Artificial Intelligence · Computer Science 2026-01-06 Chris Duffey

AI is poised to revolutionize telecommunication networks by boosting efficiency, automation, and decision-making. However, the black-box nature of most AI models introduces substantial risk, possibly deterring adoption by network operators.…

Information Theory · Computer Science 2025-04-29 Osvaldo Simeone , Sangwoo Park , Matteo Zecchin

Modern AI enables a high-level, declarative form of interaction: Users describe the intended outcome they wish an AI to produce, but do not actually create the outcome themselves. In contrast, in traditional user interfaces, users invoke…

Human-Computer Interaction · Computer Science 2024-09-18 Michael Terry , Chinmay Kulkarni , Martin Wattenberg , Lucas Dixon , Meredith Ringel Morris

The governance of frontier AI increasingly relies on controlling access to computational resources, yet the hardware-level mechanisms invoked by policy proposals remain largely unexamined from an engineering perspective. This paper bridges…

Cryptography and Security · Computer Science 2026-04-07 Samar Ansari

Responsible AI is widely considered as one of the greatest scientific challenges of our time and is key to increase the adoption of AI. Recently, a number of AI ethics principles frameworks have been published. However, without further…

Artificial Intelligence · Computer Science 2023-09-29 Qinghua Lu , Liming Zhu , Xiwei Xu , Jon Whittle , Didar Zowghi , Aurelie Jacquet

AI (super) alignment describes the challenge of ensuring (future) AI systems behave in accordance with societal norms and goals. While a quickly evolving literature is addressing biases and inequalities, the geographic variability of…

Artificial Intelligence · Computer Science 2025-08-08 Krzysztof Janowicz , Zilong Liu , Gengchen Mai , Zhangyu Wang , Ivan Majic , Alexandra Fortacz , Grant McKenzie , Song Gao

Recent years have seen significant progress in the realm of robot autonomy, accompanied by the expanding reach of robotic technologies. However, the emergence of new deployment domains brings unprecedented challenges in ensuring safe…

Systems and Control · Electrical Eng. & Systems 2023-09-13 Kai-Chieh Hsu , Haimin Hu , Jaime Fernández Fisac

Deployed, autonomous AI systems must often evaluate multiple plausible courses of action (extended sequences of behavior) in novel or under-specified contexts. Despite extensive training, these systems will inevitably encounter scenarios…

Artificial Intelligence · Computer Science 2025-11-19 Steven J. Jones , Robert E. Wray , John E. Laird