English
Related papers

Related papers: An Approach to Technical AGI Safety and Security

200 papers

Existing evaluations of AI misuse safeguards provide a patchwork of evidence that is often difficult to connect to real-world decisions. To bridge this gap, we describe an end-to-end argument (a "safety case") that misuse safeguards reduce…

Machine Learning · Computer Science 2025-05-26 Joshua Clymer , Jonah Weinbaum , Robert Kirk , Kimberly Mai , Selena Zhang , Xander Davies

The AI alignment problem, which focusses on ensuring that artificial intelligence (AI), including AGI and ASI, systems act according to human values, presents profound challenges. With the progression from narrow AI to Artificial General…

Artificial Intelligence · Computer Science 2025-07-25 Alberto Hernández-Espinosa , Felipe S. Abrahão , Olaf Witkowski , Hector Zenil

Human oversight of AI is promoted as a safeguard against risks such as inaccurate outputs, system malfunctions, or violations of fundamental rights, and is mandated in regulation like the European AI Act. Yet debates on human oversight have…

Cryptography and Security · Computer Science 2026-03-06 Jonas C. Ditz , Veronika Lazar , Elmar Lichtmeß , Carola Plesch , Matthias Heck , Kevin Baum , Markus Langer

Rapid advancements in artificial intelligence (AI) have sparked growing concerns among experts, policymakers, and world leaders regarding the potential for increasingly advanced AI systems to pose catastrophic risks. Although numerous risks…

Computers and Society · Computer Science 2023-10-11 Dan Hendrycks , Mantas Mazeika , Thomas Woodside

Artificial General Intelligence (AGI) is increasingly being discussed not only as a tool, but also as a potential subject with personal and therefore moral status. In our opinion, the currently dominant alignment strategies, which focus on…

Artificial Intelligence · Computer Science 2026-04-17 Till Mossakowski , Helena Esther Grass

In this paper we discuss how systems with Artificial Intelligence (AI) can undergo safety assessment. This is relevant, if AI is used in safety related applications. Taking a deeper look into AI models, we show, that many models of…

Artificial Intelligence · Computer Science 2021-05-17 Jens Braband , Hendrik Schäbe

Generative Artificial Intelligence (GenAI) presents significant advancements but also introduces novel security challenges, particularly within agentic workflows where AI agents operate autonomously. These risks escalate in multi-agent…

Cryptography and Security · Computer Science 2025-06-24 Sunil Kumar Jang Bahadur , Gopala Dhar

Recent AI progress has outpaced expectations, with some experts now predicting AI that matches or exceeds human capabilities in all cognitive areas (AGI) could emerge this decade, potentially posing grave national and global security…

Computers and Society · Computer Science 2025-07-30 Sarah Hastings-Woodhouse

As generative large model capabilities advance, safety concerns become more pronounced in their outputs. To ensure the sustainable growth of the AI ecosystem, it's imperative to undertake a holistic evaluation and refinement of associated…

Artificial Intelligence · Computer Science 2023-12-01 Jiawen Deng , Jiale Cheng , Hao Sun , Zhexin Zhang , Minlie Huang

Artificial intelligence risks are multidimensional in nature, as the same risk scenarios may have legal, operational, and financial risk dimensions. With the emergence of new AI regulations, the state of the art of artificial intelligence…

Computers and Society · Computer Science 2025-09-24 Luis Enriquez Alvarez

Artificial intelligence (AI) has the potential to greatly improve society, but as with any powerful technology, it comes with heightened risks and responsibilities. Current AI research lacks a systematic discussion of how to manage…

Computers and Society · Computer Science 2022-09-21 Dan Hendrycks , Mantas Mazeika

Generative artificial intelligence (GenAI) has the potential to improve healthcare through automation that enhances the quality and safety of patient care. Powered by foundation models that have been pretrained and can generate complex…

Computers and Society · Computer Science 2024-07-25 Laleh Jalilian , Daniel McDuff , Achuta Kadambi

AI systems are often introduced with high expectations, yet many fail to deliver, resulting in unintended harm and missed opportunities for benefit. We frequently observe significant "AI Mismatches", where the system's actual performance…

Human-Computer Interaction · Computer Science 2025-04-16 Devansh Saxena , Ji-Youn Jung , Jodi Forlizzi , Kenneth Holstein , John Zimmerman

This paper proposes a novel framework for developing safe Artificial General Intelligence (AGI) by combining Active Inference principles with Large Language Models (LLMs). We argue that traditional approaches to AI safety, focused on…

Artificial Intelligence · Computer Science 2025-08-11 Bo Wen

As a result of rapidly accelerating AI capabilities, over the past year, national governments and multinational bodies have announced efforts to address safety, security and ethics issues related to AI models. One high priority among these…

Computers and Society · Computer Science 2026-05-19 Jaspreet Pannu , Doni Bloomfield , Alex Zhu , Robert MacKnight , Gabe Gomes , Anita Cicero , Thomas V. Inglesby

Embedded into information systems, artificial intelligence (AI) faces security threats that exploit AI-specific vulnerabilities. This paper provides an accessible overview of adversarial attacks unique to predictive and generative AI…

Cryptography and Security · Computer Science 2025-07-01 Naoto Kiribuchi , Kengo Zenitani , Takayuki Semitsu

AI alignment aims to make AI systems behave in line with human intentions and values. As AI systems grow more capable, so do risks from misalignment. To provide a comprehensive and up-to-date overview of the alignment field, in this survey,…

AI alignment work is important from both a commercial and a safety lens. With this paper, we aim to help actors who support alignment efforts to make these efforts as effective as possible, and to avoid potential adverse effects. We begin…

Computers and Society · Computer Science 2023-12-18 Oliver Guest , Michael Aird , Seán Ó hÉigeartaigh

Due to its general-purpose nature, Generative AI is applied in an ever-growing set of domains and tasks, leading to an expanding set of risks of harm impacting people, communities, society, and the environment. These risks may arise due to…

Computers and Society · Computer Science 2026-04-27 Megan Li , Wendy Bickersteth , Ningjing Tang , Jason Hong , Lorrie Cranor , Hong Shen , Hoda Heidari

The malicious use or malfunction of advanced general-purpose AI (GPAI) poses risks that, according to leading experts, could lead to the 'marginalisation or extinction of humanity.' To address these risks, there are an increasing number of…

Computers and Society · Computer Science 2025-03-26 Rebecca Scholefield , Samuel Martin , Otto Barten