Zusammenfassung
Künstliche Intelligenz (KI) bringt neue Sicherheitsherausforderungen mit sich, denen sich sowohl Anbieter als auch Betreiber stellen müssen. Dieser Beitrag gibt einen Überblick über spezifische Schutzziele für KI-Systeme. Es werden potenzielle Risiken erläutert, vor denen KI-Systeme geschützt werden müssen, sowie Maßnahmen, mit denen diese Schutzziele erreicht werden können. Darüber hinaus werden potenzielle Nebenwirkungen diskutiert.
This is a preview of subscription content, log in via an institution to check access.
Explore related subjects
Discover the latest articles and news from researchers in related subjects, suggested using machine learning.Literatur
ISO/IEC 27000:2018 (E). (2018). Information technology – Security techniques – Information security management systems – Overview and vocabulary. ISO/IEC.
ITU Security in Telecommunications and Information Technology: An overview of issues and the deployment of existing ITU-T Recommendations for secure telecommunications, ITU-T, Geneva (2012) – ITU-T X-800.
OWASP AI Exchange, https://owaspai.org/docs/ai_security_overview/
Nicholas Carlini, Florian Tramèr, Eric Wallace, Matthew Jagielski, Ariel Herbert-Voss, Katherine Lee, Adam Roberts, Tom B. Brown, Dawn Song, Úlfar Erlingsson, Alina Oprea, & Colin Raffel (2021). Extracting Training Data from Large Language Models. In 30th USENIX Security Symposium, USENIX Security 2021, August 11-13, 2021 (pp. 2633–2650). USENIX Association.
Milad Nasr, Nicholas Carlini, Jonathan Hayase, Matthew Jagielski, A. Feder Cooper, Daphne Ippolito, Christopher A. Choquette-Choo, Eric Wallace, Florian Tramèr, & Katherine Lee (2023). Scalable Extraction of Training Data from (Production) Language Models. CoRR, abs/2311.17035.
Nicholas Carlini, Daniel Paleka, Krishnamurthy Dj Dvijotham, Thomas Steinke, Jonathan Hayase, A. Feder Cooper, Katherine Lee, Matthew Jagielski, Milad Nasr, Arthur Conmy, Eric Wallace, David Rolnick, & Florian Tramèr (2024). Stealing Part of a Production Language Model. In Forty-first International Conference on Machine Learning, ICML 2024, Vienna, Austria, July 21-27, 2024. OpenReview.net.
Yash Sharma, & Pin-Yu Chen (2018). Bypassing Feature Squeezing by Increasing Adversary Strength. CoRR, abs/1803.09868.
Shreya Goyal, Sumanth Doddapaneni, Mitesh M. Khapra, & Balaraman Ravindran (2023). A Survey of Adversarial Defenses and Robustness in NLP. ACM Comput. Surv., 55(14s), 332:1–332:39.
Lu, Z., Hu, H., Huo, S., & Li, S. (2022). Ensemble Learning Methods of Adversarial Attacks and Defenses in Computer Vision: Recent Progress. In 2021 International Conference on Advanced Computing and Endogenous Security (pp. 1-10).
Sumanth Dathathri, Abigail See, Sumedh Ghaisas, Po-Sen Huang, Rob McAdam, Johannes Welbl, Vandana Bachani, Alex Kaskasoli, Robert Stanforth, Tatiana Matejovicova, Jamie Hayes, Nidhi Vyas, Majd Al Merey, Jonah Brown-Cohen, Rudy Bunel, Borja Balle, A. Taylan Cemgil, Zahra Ahmed, Kitty Stacpoole, Ilia Shumailov, Ciprian Baetu, Sven Gowal, Demis Hassabis, & Pushmeet Kohli (2024). Scalable watermarking for identifying large language model outputs. Nature, 634(8035), 818–823.
Xu, W., Evans, D., & Qi, Y. (2018). Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networks. 25th Annual Network and Distributed System Security Symposium, NDSS 2018, San Diego, California, USA, February 18-21, 2018.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Halvani, O., Müller, L. Sicherheitsanforderungen an KI-Systeme. Datenschutz Datensich 49, 302–306 (2025). https://doi.org/10.1007/s11623-025-2092-5
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11623-025-2092-5