Buchumschlag

Small models, big threats: Characterizing safety challenges from low-compute AI models

Fuente: arXiv

Gespeichert in:

Bibliographische Detailangaben
1. Verfasser:	Puri, Prateek
Format:	Preprint
Veröffentlicht:	2026
Schlagworte:	Computers and Society
Online-Zugang:	Acceder al recurso
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Ähnliche Einträge

Measurement challenges in AI catastrophic risk governance and safety frameworks
von: Kasirzadeh, Atoosa
Veröffentlicht: (2024)

The recessionary pressures of generative AI: A threat to wellbeing
von: Occhipinti, Jo-An, et al.
Veröffentlicht: (2024)

The threat of analytic flexibility in using large language models to simulate human data
von: Cummins, Jamie
Veröffentlicht: (2025)

Safety challenges of AI in medicine in the era of large language models
von: Wang, Xiaoye, et al.
Veröffentlicht: (2024)

Irresponsible AI: big tech's influence on AI research and associated impacts
von: Hernandez-Garcia, Alex, et al.
Veröffentlicht: (2025)

Characterizing and modeling harms from interactions with design patterns in AI interfaces
von: Ibrahim, Lujain, et al.
Veröffentlicht: (2024)

AI Emergency Preparedness: Examining the federal government's ability to detect and respond to AI-related national security threats
von: Wasil, Akash, et al.
Veröffentlicht: (2024)

Dynamic safety cases for frontier AI
von: Cârlan, Carmen, et al.
Veröffentlicht: (2024)

Deep opacity and AI: A threat to XAI and to privacy protection mechanisms
von: Müller, Vincent C.
Veröffentlicht: (2025)

AI threats to national security can be countered through an incident regime
von: Ortega, Alejandro
Veröffentlicht: (2025)

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

Foundation models may exhibit staged progression in novel CBRN threat disclosure
von: Esvelt, Kevin M
Veröffentlicht: (2025)

Digital Lifelong Learning in the Age of AI: Trends and Insights
von: Puri, Geeta, et al.
Veröffentlicht: (2026)

AI as a Medical Ally: Evaluating ChatGPT's Usage and Impact in Indian Healthcare
von: Raina, Aryaman, et al.
Veröffentlicht: (2024)

Transforming disaster risk reduction with AI and big data: Legal and interdisciplinary perspectives
von: Chun, Kwok P, et al.
Veröffentlicht: (2024)

Is a model equivalent to its computer implementation?
von: Hiesmayr, Beatrix C., et al.
Veröffentlicht: (2024)

Including frameworks of public health ethics in computational modelling of infectious disease interventions
von: Zarebski, Alexander E., et al.
Veröffentlicht: (2025)

Third-party compliance reviews for frontier AI safety frameworks
von: Homewood, Aidan, et al.
Veröffentlicht: (2025)

A systematic review of research on large language models for computer programming education
von: Zhu, Meina, et al.
Veröffentlicht: (2025)

A risk model and analysis method for the psychological safety of human and autonomous vehicles interaction
von: Sirgabsou, Yandika, et al.
Veröffentlicht: (2024)

The rising costs of training frontier AI models
von: Cottier, Ben, et al.
Veröffentlicht: (2024)

Fairness in AI: challenges in bridging the gap between algorithms and law
von: Giannopoulos, Giorgos, et al.
Veröffentlicht: (2024)

Sleeper Social Bots: a new generation of AI disinformation bots are already a political threat
von: Doshi, Jaiv, et al.
Veröffentlicht: (2024)

Large Language Models Enable Design of Personalized Nudges across Cultures
von: Maksimenko, Vladimir, et al.
Veröffentlicht: (2025)

Defining bias in AI-systems: Biased models are fair models
von: Lindloff, Chiara, et al.
Veröffentlicht: (2025)

The coordination gap in frontier AI safety policies
von: Mengesha, Isaak
Veröffentlicht: (2026)

A survey on fairness of large language models in e-commerce: progress, application, and challenge
von: Ren, Qingyang, et al.
Veröffentlicht: (2024)

Affirmative safety: An approach to risk management for high-risk AI
von: Wasil, Akash R., et al.
Veröffentlicht: (2024)

A cross-regional review of AI safety regulations in the commercial aviation
von: Barr, Penny A., et al.
Veröffentlicht: (2025)

How do digital threats change requirements for the software industry?
von: Halttunen, Veikko
Veröffentlicht: (2024)

A computational model for gender asset gap management with a focus on gender disparity in land acquisition and land tenure security
von: Ogundare, Oluwatosin, et al.
Veröffentlicht: (2024)

AI-AI Bias: large language models favor communications generated by large language models
von: Laurito, Walter, et al.
Veröffentlicht: (2024)

Generative AI has lowered the barriers to computational social sciences
von: Zhang, Yongjun
Veröffentlicht: (2023)

A semantic embedding space based on large language models for modelling human beliefs
von: Lee, Byunghwee, et al.
Veröffentlicht: (2024)

Mitigating biases in big mobility data: a case study of monitoring large-scale transit systems
von: Wang, Feilong, et al.
Veröffentlicht: (2024)

Adoption of smartphones among older adults and the role of perceived threat of cyberattacks
von: Pucer, Patrik, et al.
Veröffentlicht: (2024)

The potential functions of an international institution for AI safety. Insights from adjacent policy areas and recent trends
von: De Castris, A. Leone, et al.
Veröffentlicht: (2024)

Characterizing AI Fact-Checkers and Their Contributions on Community Notes
von: Gong, Yilin, et al.
Veröffentlicht: (2026)

STAMP/STPA Informed Characterization of Factors Leading to Loss of Control in AI Systems
von: Barrett, Steve, et al.
Veröffentlicht: (2025)

Comprehensive AI governance requires addressing non-model gains
von: Goemans, Arthur, et al.
Veröffentlicht: (2026)