Imagen de Portada

Securing External Deeper-than-black-box GPAI Evaluations

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Tlaie, Alejandro, Farrell, Jimmy
Formato:	Preprint
Publicado:	2025
Materias:	Computers and Society
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Using AI Alignment Theory to understand the potential pitfalls of regulatory frameworks
por: Tlaie, Alejandro
Publicado: (2024)

Expanding External Access To Frontier AI Models For Dangerous Capability Evaluations
por: Charnock, Jacob, et al.
Publicado: (2026)

GPAI Evaluations Standards Taskforce: Towards Effective AI Governance
por: Paskov, Patricia, et al.
Publicado: (2024)

A Blueprint for an EU Ecosystem of Secure, Deep and External AI Audits
por: Tlaie, Alejandro
Publicado: (2025)

Preliminary suggestions for rigorous GPAI model evaluations
por: Paskov, Patricia, et al.
Publicado: (2025)

Mapping Industry Practices to the EU AI Act's GPAI Code of Practice Safety and Security Measures
por: Stelling, Lily, et al.
Publicado: (2025)

Assessing confidence in frontier AI safety cases
por: Barrett, Stephen, et al.
Publicado: (2025)

Enabling Responsible, Secure and Sustainable Healthcare AI - A Strategic Framework for Clinical and Operational Impact
por: Joseph, Jimmy
Publicado: (2025)

AI Risk-Management Standards Profile for General-Purpose AI (GPAI) and Foundation Models
por: Barrett, Anthony M., et al.
Publicado: (2025)

Exploring and steering the moral compass of Large Language Models
por: Tlaie, Alejandro
Publicado: (2024)

Quality Assessment of Public Summary of Training Content for GPAI models required by AI Act Article 53(1)(d)
por: Blankvoort, Dick A. H., et al.
Publicado: (2026)

A Methodology for Quantitative AI Risk Modeling
por: Murray, Malcolm, et al.
Publicado: (2025)

The Role of Risk Modeling in Advanced AI Risk Management
por: Touzet, Chloé, et al.
Publicado: (2025)

External Evaluation of Discrimination Mitigation Efforts in Meta's Ad Delivery
por: Imana, Basileal, et al.
Publicado: (2025)

Federated learning, ethics, and the double black box problem in medical AI
por: Hatherley, Joshua, et al.
Publicado: (2025)

An External Fairness Evaluation of LinkedIn Talent Search
por: Behzad, Tina, et al.
Publicado: (2025)

Descriptions of women are longer than that of men: An analysis of gender portrayal prompts in Stable Diffusion
por: Asadchy, Yan, et al.
Publicado: (2024)

Creating and Evaluating Privacy and Security Micro-Lessons for Elementary School Children
por: Gao, Lan, et al.
Publicado: (2025)

Lessons from External Review of DeepMind's Scheming Inability Safety Case
por: Barrett, Stephen, et al.
Publicado: (2026)

Safe for Whom? Rethinking How We Evaluate the Safety of LLMs for Real Users
por: Kempermann, Manon, et al.
Publicado: (2025)

Toward Quantitative Modeling of Cybersecurity Risks Due to AI Misuse
por: Barrett, Steve, et al.
Publicado: (2025)

FORTRESS: Frontier Risk Evaluation for National Security and Public Safety
por: Knight, Christina Q., et al.
Publicado: (2025)

Assessing the Impact of External and Internal Factors on Emergency Department Overcrowding
por: Ahmed, Abdulaziz, et al.
Publicado: (2025)

Small Models Achieve Large Language Model Performance: Evaluating Reasoning-Enabled AI for Secure Child Welfare Research
por: Qi, Zia, et al.
Publicado: (2025)

Purer than pure: how purity reshapes the upstream materiality of the semiconductor industry
por: Roussilhe, Gauthier, et al.
Publicado: (2025)

From Replacement to Orchestration: A Socio-Technical Architecture for Agentic AI in Corporate R&D
por: Boussaid, Haithem, et al.
Publicado: (2026)

Evaluating Organization Security: User Stories of European Union NIS2 Directive
por: Seeba, Mari, et al.
Publicado: (2025)

Secure On-Premise Deployment of Open-Weights Large Language Models in Radiology: An Isolation-First Architecture with Prospective Pilot Evaluation
por: Nowak, Sebastian, et al.
Publicado: (2026)

Intimacy as Service, Harm as Externality: Critical Perspectives on AI Companion Platform Accountability
por: Eom, Dayeon, et al.
Publicado: (2026)

Rethinking Optimization: A Systems-Based Approach to Social Externalities
por: Nokhiz, Pegah, et al.
Publicado: (2025)

Exploring the Adversarial Robustness of Face Forgery Detection with Decision-based Black-box Attacks
por: Chen, Zhaoyu, et al.
Publicado: (2023)

Online search is more likely to lead students to validate true news than to refute false ones
por: Bouleimen, Azza, et al.
Publicado: (2023)

European Football Player Valuation: Integrating Financial Models and Network Theory
por: Cohen, Albert, et al.
Publicado: (2023)

Assurance of Frontier AI Built for National Security
por: Pistillo, Matteo, et al.
Publicado: (2025)

When Can We Trust LLMs in Mental Health? Large-Scale Benchmarks for Reliable LLM Evaluation
por: Badawi, Abeer, et al.
Publicado: (2025)

More than Carbon: Cradle-to-Grave environmental impacts of GenAI training on the Nvidia A100 GPU
por: Falk, Sophia, et al.
Publicado: (2025)

A New Exploration into Chinese Characters: from Simplification to Deeper Understanding
por: Gong, Wen G.
Publicado: (2025)

An Empirical Analysis on the Use and Reporting of National Security Letters
por: Bellon, Alex, et al.
Publicado: (2024)

MoReBench: Evaluating Procedural and Pluralistic Moral Reasoning in Language Models, More than Outcomes
por: Chiu, Yu Ying, et al.
Publicado: (2025)

Transparency, Security, and Workplace Training & Awareness in the Age of Generative AI
por: Vaishnav, Lakshika, et al.
Publicado: (2024)