Abstract
With the recent advances in 5G and 6G communications and the increasing need for immersive interactions due to pandemic, new use cases such as All-Senses meeting are emerging. To realize these use cases, numerous sensors, actuators, and virtual reality devices are used. Additionally, artificial intelligence (AI) and machine learning (ML) including generative AI can be used to analyze large amount of data generated by 6G networks and devices to enable new applications and services. While AI/ML technologies are evolving, they do not have the same level of security as well-known information technology components. So, AI/ML threats and their impacts can be overlooked. On the other hand, due to inherent characteristics of AI/ML components and design of AI/ML pipeline, AI/ML services can be a target for sophisticated attacks. In order to provide a holistic security view, the effect of AI/ML components should be investigated, threats should be identified, and countermeasures should be planned. Therefore, in this study, which is an extended version of our recent study (Karaçay et al. 2023), we shed the light on the use of AI/ML services including generative large language model scenarios in All-Senses meeting use case and their security aspects by carrying out a threat modeling using the STRIDE framework and attack tree methodology. Additionally, we point out some countermeasures for identified threats.
Similar content being viewed by others
Data availability
No datasets were generated or analyzed during the current study.
References
Karaçay, L, Laaroussi Z, Ujjwal S, Soykan EU (2023) On the security of 6G use cases: AI/ML-specific threat modeling of All-Senses meeting. In: 2023 2nd International conference on 6g networking (6GNet), pp 1–8. https://doi.org/10.1109/6GNet58894.2023.10317758
Khorsandi BM (2022) Targets and requirements for 6G - initial E2E architecture. report, European Union’s Horizon 2020 research and innovation programme. https://hexa-x.eu/wp-content/uploads/2022/03/Hexa-X_D1.3.pdf
Kononenko D, Lempitsky V (2015) Learning to look up: realtime monocular gaze correction using machine learning. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4667–4675
Lombardi S, Simon T, Saragih J, Schwartz G, Lehrmann A, Sheikh Y (2019) Neural volumes: learning dynamic renderable volumes from images. ACM Trans Graph 38(4). https://doi.org/10.1145/3306346.3323020
Mauri L, Damiani E (2022) Modeling threats to AI-ML systems using STRIDE. Sensors 22(17):6662
Laaroussi Z, Ustundag Soykan E, Liljenstam M, Gülen U, Karaçay L, Tomur E (2022) On the security of 6G use cases: threat analysis of ’All-Senses Meeting’.In: 2022 IEEE 19th annual consumer communications & networking conference (CCNC), pp 1–6. https://doi.org/10.1109/CCNC49033.2022.9700673
Shevchenko N, Chick TA, O’Riordan P, Scanlon TP, Woody C (2018) Threat modeling: a summary of available methods. Technical report, Carnegie Mellon University Software Engineering Institute Pittsburgh United
Lawrence J, Goldman DB, Achar S, Blascovich GM, Desloge JG, Fortes T, Gomez EM, Häberling S, Hoppe H, Huibers A, Knaus C, Kuschak B, Martin-Brualla R, Nover H, Russell AI, Seitz SM, Tong K (2021) Project Starline: a high-fidelity telepresence system. ACM Trans Graph (Proc SIGGRAPH Asia) 40(6)
Akyildiz IF, Guo H (2022) Holographic-type communication: a new challenge for the next decade
Clemm A, Vega MT, Ravuri HK, Wauters T, Turck FD (2020) Toward truly immersive holographic-type communication: challenges and solutions. IEEE Commun Mag 58(1):93–99. https://doi.org/10.1109/MCOM.001.1900272
You D, Doan TV, Torre R, Mehrabi M, Kropp A, Nguyen V, Salah H, Nguyen GT, Fitzek FHP (2019) Fog computing as an enabler for immersive media: service scenarios and research opportunities. IEEE Access 7:65797–65810. https://doi.org/10.1109/ACCESS.2019.2917291
Shi L, Li B, Kim C, Kellnhofer P (2021) Author Correction: Towards real-time photorealistic 3D holography with deep neural networks. Nature 593(7858):13–13. https://doi.org/10.1038/s41586-021-03476-5
Patel K, Mehta D, Mistry C, Gupta R, Tanwar S, Kumar N, Alazab M (2020) Facial sentiment analysis using AI techniques: state-of-the-art, taxonomies, and challenges. IEEE Access 8:90495–90519. https://doi.org/10.1109/ACCESS.2020.2993803
NVIDIA (2020) NVIDIA announces cloud-AI video-streaming platform to better connect millions working and studying remotely
Martinek R, Kelnar M, Vanus J, Koudelka P, Bilik P, Koziorek J, Zidek J (2015) Adaptive noise suppression in voice communication using a neuro-fuzzy inference system. In: 2015 38th International conference on telecommunications and signal processing (TSP), pp 382–386. https://doi.org/10.1109/TSP.2015.7296288
MPAI Community. http://mpai.community
Bibhudatta, D (2023) Generative AI will transform virtual meetings
Hasan R, Hasan R (2021) Towards a threat model and security analysis of video conferencing systems. In: 2021 IEEE 18th annual consumer communications & networking conference (CCNC), pp 1–4. IEEE
Isobe T, Ito R (2021) Security analysis of end-to-end encryption for zoom meetings. IEEE Access 9:90677–90689
Ling C, Balcı U, Blackburn J, Stringhini G (2021) A first look at Zoombombing. In: 2021 IEEE symposium on security and privacy (SP), pp 1452–1467. https://doi.org/10.1109/SP40001.2021.00061
Qamar S, Anwar Z, Afzal M (2023) A systematic threat analysis and defense strategies for the metaverse and extended reality systems. Comput Secur 103127
Challenges AC (2020) AI cybersecurity challenges,threat landscape for artificial intelligence. report, European Union Agency for Cybersecurity, ENISA. https://www.enisa.europa.eu/publications/artificial-intelligence-cybersecurity-challenges
Tabassi E, Burns KJ, Hadjimichael M, Molina-Markham AD, Sexton JT (2019) A taxonomy and terminology of adversarial machine learning. NIST IR, 1–29
Papernot N (2018) A marauder’s map of security and privacy in machine learning: an overview of current and future research directions for making machine learning secure and private. In: Proceedings of the 11th ACM workshop on artificial intelligence and security, pp 1–1
Papernot N, McDaniel P, Sinha A, Wellman MP (2018) SoK: security and privacy in machine learning. In: 2018 IEEE european symposium on security and privacy (EuroS & P), pp 399–414. IEEE
Barreno M, Nelson B, Sears R, Joseph AD, Tygar JD (2006) Can machine learning be secure? In: Proceedings of the 2006 ACM symposium on information, computer and communications security, pp 16–25
Mauri L, Damiani E (2021) STRIDE-AI: an approach to identifying vulnerabilities of machine learning assets. In: 2021 IEEE international conference on cyber security and resilience (CSR), pp 147–154. IEEE
Industry Specification Group (ISG) Securing artificial intelligence (SAI) (2021) Securing Artificial Intelligence (SAI). ETSI, France
Brown T, Mann B, Ryder N, Subbiah M, Kaplan JDea (2020) Language models are few-shot learners. In: Larochelle, H, Ranzato M, Hadsell R, Balcan MF, Lin H (eds) Advances in neural information processing systems, vol 33, pp 1877–1901. Curran Associates, Inc., ???. https://proceedings.neurips.cc/paper_files/paper/2020/file/1457c0d6bfcb4967418bfb8ac142f64a-Paper.pdf
Selin J (2019) Evaluation of threat modeling methodologies
National Cyber Security Center (2023) Using attack trees to understand cyber security risk. https://www.ncsc.gov.uk/collection/risk-management/using-attack-trees-to-understand-cyber-security-risk
Microsoft (2021) Microsoft AI Security Risk Assessment, Best Practices and Guidance to Secure AI Systems
Casella D, Lawson L (2022) AI and privacy: everything you need to know about trust and technology. https://www.ericsson.com/en/blog/2022/8/ai-and-privacy-everything-you-need-to-know
Boyd C (2022) Meta blows safety bubble around users after reports of sexual harassment
Hong S, Chandrasekaran V, Kaya Y, Dumitras T, Papernot N (2020) On the effectiveness of mitigating data poisoning attacks with gradient shaping. ArXiv:2002.11497
Nelson B, Barreno M, Chi FJ, Joseph AD, Rubinstein BIP, Saini U, Sutton C, Tygar JD, Xia K (2008) Exploiting machine learning to subvert your spam filter. In: USENIX workshop on large-scale exploits and emergent threats
Oprea A, Vassilev A (2023) Adversarial machine learning: a taxonomy and terminology of attacks and mitigations (draft). Technical report, National Institute of Standards and Technology
Goodfellow I, Bengio Y, Courville A (2016) Deep learning. MIT press, ???
Ustundag Soykan E, Karaçay L, Karakoç F, Tomur E (2022) A survey and guideline on privacy enhancing technologies for collaborative machine learning. IEEE Access 10:97495–97519. https://doi.org/10.1109/ACCESS.2022.3204037
Foundation TO (2023) OWASP API Security Project.https://owasp.org/www-project-api-security/
Foundation TO (2023) OWASP top 10 for large language model applications.https://owasp.org/www-project-top-10-for-large-language-model-applications
Funding
This work was supported by the Scientific and Technological Research Council of Turkey (TUBITAK) through the 1515 Frontier Research and Development Laboratories Support Program under Project 5169902, and has been partly funded by the European Commission through the Horizon Europe/JU SNS project Hexa-X-II (Grant Agreement no. 101095759).
Author information
Authors and Affiliations
Contributions
All authors contributed equally to the publication and reviewed the manuscript.
Corresponding author
Ethics declarations
Conflict of interest
The authors declare no competing interests.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Karaçay, L., Laaroussi, Z., ujjwal, S. et al. Guarding 6G use cases: a deep dive into AI/ML threats in All-Senses meeting. Ann. Telecommun. (2024). https://doi.org/10.1007/s12243-024-01031-7
Received:
Accepted:
Published:
DOI: https://doi.org/10.1007/s12243-024-01031-7