Communications, Electronics and Sensing Systems logo

Articles

Vol. 1 No. 4 (2026)

Adversarial Robustness Evaluation for Vision Foundation Models and Generative Artificial Intelligence Systems

Submitted
July 19, 2026
Published
August 7, 2026

Abstract

The rapid advancement of artificial intelligence has ushered in a new era dominated by vision foundation models and generative artificial intelligence systems. These architectures exhibit unprecedented capabilities in image synthesis, classification, and cross-modal understanding. However, their increasing deployment in safety-critical domains raises substantial concerns regarding their susceptibility to adversarial perturbations. This paper presents a comprehensive evaluation of adversarial robustness specifically tailored to the unique vulnerabilities of large-scale vision and generative models. By systematically analyzing the attack surfaces, including input space perturbations and prompt injection techniques, we illuminate the complex failure modes inherent in these advanced systems. Our investigation encompasses a rigorous methodological framework that assesses the degradation of model performance under various threat models, ranging from white-box gradient-based attacks to black-box query-based methodologies. The extensive analysis demonstrates that while foundation models possess remarkable generalization capabilities, they simultaneously inherit and amplify adversarial vulnerabilities from their pre-training corpora. Furthermore, we explore the intricate balance between generative fidelity and adversarial resilience, revealing significant trade-offs that complicate the development of robust defensive mechanisms. Through empirical investigation and theoretical analysis, this research provides critical insights into the limitations of current generative architectures and proposes foundational principles for the design of next-generation, robust artificial intelligence systems.

References

  1. 1. Liang, R., Xu, S., Xie, C., Chen, J., Ren, F., Yang, S., & Yabe, T. (2026). Abstain Mask Retain Core: Time Series Prediction by Adaptive Masking Loss with Representation Consistency. Advances in Neural Information Processing Systems, 38, 99445-99471.
  2. 2. Li, B., Zhang, R., Liang, H., Zhang, J., Zhang, J., Chen, X., ... & Wang, J. (2026). Interagent: Physics-based multi-agent command execution via diffusion on interaction graphs. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 15253-15265).
  3. 3. Yao, Y., Shu, F., Li, Z., Cheng, X., & Wu, L. (2023). Secure transmission scheme based on joint radar and communication in mobile vehicular networks. IEEE transactions on intelligent transportation systems, 24 (9), 10027-10037.
  4. 4. Zhang, Y., Zhang, Y., Zhao, M., Feng, S., & Cheung, Y. M. (2026). How to Ask the AI: A User Perspective Survey for Large Language Model Prompting.IEEE Transactions on Artificial Intelligence.
  5. 5. Li, X., Wang, P., Li, G., & Zhang, Y. (2023). Design of a novel self-test-on-chip interface ASIC for capacitive accelerometers. IEEE Transactions on Circuits and Systems I: Regular Papers, 70(7), 2834-2843.
  6. 6. Wang, S., Zhang, X., Wang, P., & Li, X. (2026). Design of Magnetic Sensor Array-Based PUFs for IoT Security. IEEE Transactions on Instrumentation and Measurement, 75, 1-9.
  7. 7. Liu, C., Zhang, J., Zhang, T., Wang, Y., Zhou, H., & Jin, Q. (2026). HRIBench: Benchmarking Interaction-Centric Human-Robot Collaboration.arXiv preprint arXiv:2607.13056.
  8. 8. Jin, H., Tsai, F. S., & Martinez-Vazquez, J. (2025). Optimal expenditure decentralization for sustainable development: evidence from a 52-country panel analysis. Financial Innovation, 11(1), 111.
  9. 9. Li, X., Wang, P., Li, G., Ni, L., & Zhang, Y. (2023). Design of interface circuits and lightweight PUF for TMR sensors. IEEE Sensors Journal, 23(11), 11754-11761.
  10. 10. Zhao, Q., & Huang, Y. (2026). DAREA: A Dynamic AI-Driven Architecture for Real Estate Asset Tokenization on Blockchain.Fundamental Scientific Reports in Multidisciplinary Areas,2(02), 182-192.
  11. 11. Hu, X., Wan, Z., & Yin, Q. (2025). Token Design for Favor Trading with Dynamic Membership. Available at SSRN 6175079.
  12. 12. Issa, M. A., Chen, H., Wang, J., & Imani, M. (2024). CyberRL: Brain-inspired reinforcement learning for efficient network intrusion detection.IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems,44(1), 241-250.
  13. 13. Amodei, D., Olah, C., Steinhardt, J., Christiano, P., Schulman, J., & Mané, D. (2016). Concrete problems in AI safety. arXiv preprint arXiv:1606.06565.
  14. 14. Qu, D., Ma, Y., Yan, J., & Pyrozhenko, M. (2026). TriMeta-BFNet: A Tri-Meta Stacked Atypical-Frequency Bayesian Fourier Neural Network for Hallucination-Resistant Community Detection. Mathematics, 14 (13), 2283.
  15. 15. Ma, Y., & Qu, D. (2026, February). IMFM-GNN: Interpretable Multimodel GNN Via Fourier-Markov Dynamics for Community Detection in Sustainable Energy Networks. In 2026 International Conference on Artificial Intelligence, Computer, Data Sciences and Applications (ACDSA) (pp. 1-6). IEEE.
  16. 16. Wuyang Zhang and Shichao Pei. 2026. Your LLM Agent Can Leak Your Data: Data Exfiltration via Backdoored Tool
  17. Use. arXiv:2604.05432 [cs.CR] doi:10.48550/arXiv.2604.05432
  18. 17. Yang, W., Qin, Y., & Yang, Y. (2021). Characterizing the multicast nature of malicious flows in CCN via SIS epidemic model. IEEE Systems Journal, 16(2), 2240-2250.
  19. 18. Yang, P., Chen, W., Wang, K., Ai, L., Yang, E., & Shi, T. (2026, July). EVM-QuestBench: An Execution-Grounded Benchmark for Natural-Language Transaction Code Generation. In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)(pp. 35513-35529).
  20. 19. Tao, J., Lyu, R., & Cao, X. (2026). A Deep Learning-Based Automated Content Moderation Framework for Online Platforms.Future-Adaptive Intelligence and Lifelong Systems,1(1).
  21. 20. Luo, P., & Ding, X. (2026). C-MAPPO-TSC: A Collaborative Multi-Agent Reinforcement Learning Framework for Urban Traffic Signal Control and Congestion Mitigation. Fundamental Scientific Reports in Multidisciplinary Areas, 2 (02), 170-181.
  22. 21. Hu, X., Wan, Z., & Murthy, N. N. (2019). Dynamic pricing of limited inventories with product returns. Manufacturing & Service Operations Management, 21(3), 501-518.
  23. 22. Yang, Z., Ji, W., & Wang, Z. (2024). Adaptive joint configuration optimization for collaborative inference in edge-cloud systems. Science China Information Sciences, 67(4), 149103.
  24. 23. Long, J., Xu, Z., Jiang, T., Yao, W., Jia, S., Ma, C., & Chen, X. (2025, April). Robust SAM: on the adversarial robustness of vision foundation models. In Proceedings of the AAAI Conference on Artificial Intelligence (Vol. 39, No. 6, pp. 5775-5783).
  25. 24. Yang, Z., Liang, B., & Ji, W. (2021). An intelligent end–edge–cloud architecture for visual IoT-assisted healthcare systems. IEEE internet of things journal, 8(23), 16779-16786.
  26. 25. Zhang, Q., Gao, W., Liu, C., Yao, Y., Yan, S., Shu, F., & Jin, S. (2025). Covert transmission for active RIS-aided full-duplex UAV integrated sensing, communication, and computation systems. IEEE Journal on Selected Areas in Communications.
  27. 26. Yao, Y., Zhao, J., Li, Z., Cheng, X., & Wu, L. (2023). Jamming and eavesdropping defense scheme based on deep reinforcement learning in autonomous vehicle networks. IEEE Transactions on Information Forensics and Security, 18, 1211-1224.
  28. 27. Yang, Z., Ji, W., Guo, Q., & Wang, Z. (2023, October). Javp: Joint-aware video processing with edge-cloud collaboration for dnn inference. In Proceedings of the 31st ACM International Conference on Multimedia (pp. 9152-9160).
  29. 28. Qu, D., Ma, Y., & Wang, Y. (2026). STR-GNN: stability-regularized graph neural networks for suppressing spurious temporal variations in dynamic community detection. Scientific Reports.
  30. 29. Liao, Qiuyue, et al. "Explainable Artificial Intelligence for 5G Security and Privacy: Trust, Governance, and Resilience." (2025).
  31. 30. Ma, Y., Qu, D., & Wang, Y. (2026). HALO-GNN: hallucination-resistant temporal graph neural networks for dynamic community detection.Scientific Reports.
  32. 31. Tao, J., Lyu, R., & Cao, X. (2026). A Scalable Data Governance Architecture for Privacy-Aware Intelligent Learning Systems in Lifelong. Future-Adaptive Intelligence and Lifelong Systems, 1 (1).
  33. 32. Zhang, H., Zandsalimy, M., & Sushmita, S. (2026). Exposing LLM Safety Gaps Through Mathematical Encoding: New Attacks and Systematic Analysis.arXiv preprint arXiv:2605.03441.