English
Related papers

Related papers: When Openness Fails: Lessons from System Safety fo…

200 papers

Over the past decade, an ecosystem of measures has emerged to evaluate the social and ethical implications of AI systems, largely shaped by high-level ethics principles. These measures are developed and used in fragmented ways, without…

Human-Computer Interaction · Computer Science 2025-10-14 Shalaleh Rismani , Renee Shelby , Leah Davis , Negar Rostamzadeh , AJung Moon

The use of Artificial Intelligence (AI) in high-risk, decision-making scenarios presents technical, safety, and normative challenges; problems that may only be ameliorated by human oversight. However, notions of human oversight lack a…

As increasingly powerful generative AI systems are developed, the release method greatly varies. We propose a framework to assess six levels of access to generative AI systems: fully closed; gradual or staged access; hosted access;…

Computers and Society · Computer Science 2023-02-10 Irene Solaiman

In today's world, we need to ensure that AI systems are fair and unbiased. Our study looked at tools designed to test the fairness of software to see if they are practical and easy for software developers to use. We found that while some…

Software Engineering · Computer Science 2024-09-05 Thanh Nguyen , Luiz Fernando de Lima , Maria Teresa Badassarre , Ronnie de Souza Santos

Artificial intelligence (AI) technologies (re-)shape modern life, driving innovation in a wide range of sectors. However, some AI systems have yielded unexpected or undesirable outcomes or have been used in questionable manners. As a…

We draw on our experience working on system and software assurance and evaluation for systems important to society to summarise how safety engineering is performed in traditional critical systems, such as aircraft flight control. We analyse…

Computers and Society · Computer Science 2025-02-07 Robin Bloomfield , John Rushby

As AI systems become more advanced, companies and regulators will make difficult decisions about whether it is safe to train and deploy them. To prepare for these decisions, we investigate how developers could make a 'safety case,' which is…

Computers and Society · Computer Science 2024-03-20 Joshua Clymer , Nick Gabrieli , David Krueger , Thomas Larsen

Recent discussions and research in AI safety have increasingly emphasized the deep connection between AI safety and existential risk from advanced AI systems, suggesting that work on AI safety necessarily entails serious consideration of…

Computers and Society · Computer Science 2025-02-17 Balint Gyevnar , Atoosa Kasirzadeh

Regulatory frameworks, such as the EU AI Act, encourage openness of general-purpose AI models by offering legal exemptions for "open-source" models. Despite this legislative attention on openness, the definition of open-source foundation…

Computer Science and Game Theory · Computer Science 2025-10-27 Tori Qiu , Benjamin Laufer , Jon Kleinberg , Hoda Heidari

As AI systems appear to exhibit ever-increasing capability and generality, assessing their true potential and safety becomes paramount. This paper contends that the prevalent evaluation methods for these systems are fundamentally…

Artificial Intelligence · Computer Science 2024-07-15 John Burden

In this work, we present and analyze reported failures of artificially intelligent systems and extrapolate our analysis to future AIs. We suggest that both the frequency and the seriousness of future AI failures will steadily increase. AI…

Artificial Intelligence · Computer Science 2016-10-26 Roman V. Yampolskiy , M. S. Spellchecker

The range of application of artificial intelligence (AI) is vast, as is the potential for harm. Growing awareness of potential risks from AI systems has spurred action to address those risks, while eroding confidence in AI systems and the…

Security, privacy, and fairness have become critical in the era of data science and machine learning. More and more we see that achieving universally secure, private, and fair systems is practically impossible. We have seen for example how…

Machine Learning · Statistics 2017-05-24 Jure Sokolic , Qiang Qiu , Miguel R. D. Rodrigues , Guillermo Sapiro

When AI systems are granted the agency to take impactful actions in the real world, there is an inherent risk that these systems behave in ways that are harmful. Typically, humans specify constraints on the AI system to prevent harmful…

Human-Computer Interaction · Computer Science 2022-11-09 Travis Mandel , Jahnu Best , Randall H. Tanaka , Hiram Temple , Chansen Haili , Kayla Schlectinger , Roy Szeto

Artificial Intelligence (AI) applications are being used to predict and assess behaviour in multiple domains, such as criminal justice and consumer finance, which directly affect human well-being. However, if AI is to improve people's…

Other Computer Science · Computer Science 2019-06-12 Andrea Aler Tubella , Andreas Theodorou , Virginia Dignum , Frank Dignum

Prominent AI companies are producing 'safety frameworks' as a type of voluntary self-governance. These statements purport to establish risk thresholds and safety procedures for the development and deployment of highly capable AI.…

Computers and Society · Computer Science 2025-10-14 Sam Coggins , Alexander K. Saeri , Katherine A. Daniell , Lorenn P. Ruster , Jessie Liu , Jenny L. Davis

As AI systems advance and integrate into society, well-designed and transparent evaluations are becoming essential tools in AI governance, informing decisions by providing evidence about system capabilities and risks. Yet there remains a…

In recent years there has been a tremendous surge in the general capabilities of AI systems, mainly fuelled by training foundation models on internetscale data. Nevertheless, the creation of openended, ever self-improving AI remains…

Artificial Intelligence (AI) Safety Institutes and governments worldwide are deciding whether they evaluate advanced AI themselves, support a private evaluation ecosystem or do both. Evaluation regimes have been established in a wide range…

Computers and Society · Computer Science 2025-08-06 Merlin Stein , Milan Gandhi , Theresa Kriecherbauer , Amin Oueslati , Robert Trager

Safety cases for frontier AI systems should provide a convincing argument, supported by evidence, that the risk of harm is within an acceptable bound. When developers author their own safety cases, confirmation bias and conflicted…