A Narrative Review of Artificial Intelligence Vulnerabilities in Cybersecurity

المؤلفون

  • Saad Mohamed Lafi المؤلف
  • Fouzi A. Abughoufa المؤلف

DOI:

https://doi.org/10.59992/IJSR.2026.v5n11p5

الكلمات المفتاحية:

Adversarial Machine Learning، Cybersecurity، Data Poisoning، Prompt Injection، Large Language Models، Model Extraction، Narrative Review

الملخص

Artificial intelligence is used in malware classification traffic analysis software development and security decision support. Yet conventional accuracy metrics do not capture the attack surfaces introduced by these applications. This narrative review critically examines 35 purposively selected studies published between 2020 and 2026. Primary records were verified against publisher proceedings institutional and author sources. The corpus comprises 33 peer-reviewed publications and two identified preprints covering evasion poisoning privacy leakage model extraction language-model injection and evaluation assurance. The analysis distinguishes findings from security applications from mechanisms established in general machine -learning and agent benchmarks. Across these settings vulnerability depends on an attacker’s access whether manipulations are valid within the application domain, and whether an erroneous output can cross an authorization boundary. Malware attacks that preserve functionality and traffic attacks that respect domain constraints offer stronger evidence of feasibility than perturbations confined to feature space. Retrieval and persistent memory extend the scope for poisoning beyond training. Agent benchmarks, in turn, highlight the need to assess authorized task completion separately from unauthorized actions. Contrasting findings from developer studies also indicate that insecure model output is not a uniform measure of harm to users. The proposed lifecycle assurance framework brings together data provenance realistic adaptive evaluation restricted privileges and monitoring over time. The purposive sample and heterogeneous outcomes preclude pooled estimates of attack success or claim about prevalence. Deployment decisions therefore require evidence spanning the full decision and action pipeline and robustness claims must remain limited to the conditions evaluated.

السير الشخصية للمؤلفين

  • Saad Mohamed Lafi

    Department of Soft. Engin. & Info. Syst., Faculty of Information Technology, Elmergib University, Libya

  • Fouzi A. Abughoufa

    Department of Computer, Faculty of Arts & Science, Kaser Khiar, Elmergib University, Libya

المراجع

Numbered reference style. Primary publisher or proceedings URLs are used when no DOI is supplied. References [23] and [32] are explicitly identified preprints. Bibliographic records were checked on 1 September 2026 publication years refer to the cited versions.

1. F. Pierazzi, F. Pendlebury, J. Cortellazzi, and L. Cavallaro, “Intriguing Properties of Adversarial ML Attacks in the Problem Space,” 2020 IEEE Symposium on Security and Privacy, IEEE, 2020. https://doi.org/10.1109/SP40000.2020.00073.

2. L. Demetrio, B. Biggio, G. Lagorio, F. Roli, and A. Armando, “Functionality-Preserving Black-Box Optimization of Adversarial Windows Malware,” IEEE Transactions on Information Forensics and Security, vol. 16, pp. 3469–3478, 2021.

https://doi.org/10.1109/TIFS.2021.3082330.

3. G. Severi, J. Meyer, S. Coull, and A. Oprea, “Explanation-Guided Backdoor Poisoning Attacks Against Malware Classifiers,” 30th USENIX Security Symposium, pp. 1487–1504, 2021. https://www.usenix.org/conference/usenixsecurity21/presentation/severi.

4. R. Schuster, C. Song, E. Tromer, and V. Shmatikov, “You Autocomplete Me: Poisoning Vulnerabilities in Neural Code Completion,” 30th USENIX Security Symposium, pp. 1559–1575, 2021. https://www.usenix.org/conference/usenixsecurity21/presentation/schuster.

5. D. Arp, E. Quiring, F. Pendlebury, A. Warnecke, F. Pierazzi, C. Wressnegger, L. Cavallaro, and K. Rieck, “Dos and Don’ts of Machine Learning in Computer Security,” 31st USENIX Security Symposium, pp. 3971–3988, 2022.

https://www.usenix.org/conference/usenixsecurity22/presentation/arp.

6. H. Pearce, B. Ahmad, B. Tan, B. Dolan-Gavitt, and R. Karri, “Asleep at the Keyboard? Assessing the Security of GitHub Copilot’s Code Contributions,” 2022 IEEE Symposium on Security and Privacy, pp. 754–768, 2022. https://doi.org/10.1109/SP46214.2022.9833571.

7. K. Mukherjee, J. Wiedemeier, T. Wang, J. Wei, F. Chen, M. Kim, M. Kantarcioglu, and K. Jee, “Evading Provenance-Based ML Detectors with Adversarial System Actions,” 32nd USENIX Security Symposium, pp. 1199–1216, 2023.

https://www.usenix.org/conference/usenixsecurity23/presentation/mukherjee.

8. N. Perry, M. Srivastava, D. Kumar, and D. Boneh, “Do Users Write More Insecure Code with AI Assistants?,” Proceedings of the 2023 ACM SIGSAC Conference on Computer and Communications Security, pp. 2785–2799, 2023. https://doi.org/10.1145/3576915.3623157.

9. G. Sandoval, H. Pearce, T. Nys, R. Karri, S. Garg, and B. Dolan-Gavitt, “Lost at C: A User Study on the Security Implications of Large Language Model Code Assistants,” 32nd USENIX Security Symposium, pp. 2205–2222, 2023.

https://www.usenix.org/conference/usenixsecurity23/presentation/sandoval.

10. H. Aghakhani, W. Dai, A. Manoel, X. Fernandes, A. Kharkar, C. Kruegel, G. Vigna, D. Evans, B. Zorn, and R. Sim, “TrojanPuzzle: Covertly Poisoning Code-Suggestion Models,” 2024 IEEE Symposium on Security and Privacy, IEEE, 2024. https://doi.org/10.1109/SP54263.2024.00140.

11. M. Jin and M. Apostolaki, “Robustifying ML-powered Network Classifiers with PANTS,” 34th USENIX Security Symposium, pp. 7291–7310, 2025.

https://www.usenix.org/conference/usenixsecurity25/presentation/jin-minhao.

12. J. Yan, Z. Liu, Y. Xie, S. Liang, L. Liu, and K. Xu, “CertTA: Certified Robustness Made Practical for Learning-Based Traffic Analysis,” 34th USENIX Security Symposium, pp. 7349–7368, 2025. https://www.usenix.org/conference/usenixsecurity25/presentation/yan-jinzhu.

13. E. Bagdasaryan, A. Veit, Y. Hua, D. Estrin, and V. Shmatikov, “How to Backdoor Federated Learning,” Proceedings of AISTATS, Proceedings of Machine Learning Research, vol. 108, pp. 2938–2948, 2020. https://proceedings.mlr.press/v108/bagdasaryan20a.html.

14. J. Geiping, H. Bauermeister, H. Dröge, and M. Moeller, “Inverting Gradients—How easy is it to break privacy in federated learning?,” Advances in Neural Information Processing Systems, vol. 33, NeurIPS 2020, 2020.

https://proceedings.neurips.cc/paper/2020/hash/c4ede56bbd98819ae6112b20ac6bf145-Abstract.html.

15. F. Tramèr, N. Carlini, W. Brendel, and A. Madry, “On Adaptive Attacks to Adversarial Example Defenses,” Advances in Neural Information Processing Systems, vol. 33, NeurIPS 2020, 2020. https://proceedings.neurips.cc/paper_files/paper/2020/hash/11f38f8ecd71867b42433548d1078e38-Abstract.html.

16. F. Croce and M. Hein, “Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks,” Proceedings of ICML, Proceedings of Machine Learning Research, vol. 119, pp. 2206–2216, 2020. https://proceedings.mlr.press/v119/croce20b.html.

17. N. Carlini, F. Tramèr, E. Wallace, M. Jagielski, A. Herbert-Voss, K. Lee, A. Roberts, T. Brown, D. Song, Ú. Erlingsson, A. Oprea, and C. Raffel, “Extracting Training Data from Large Language Models,” 30th USENIX Security Symposium, pp. 2633–2650, 2021.

https://www.usenix.org/conference/usenixsecurity21/presentation/carlini-extracting.

18. N. Carlini, S. Chien, M. Nasr, S. Song, A. Terzis, and F. Tramèr, “Membership Inference Attacks From First Principles,” 2022 IEEE Symposium on Security and Privacy, pp. 1897–1914, 2022. https://doi.org/10.1109/SP46214.2022.9833649.

19. F. Tramèr, R. Shokri, A. San Joaquin, H. Le, M. Jagielski, S. Hong, and N. Carlini, “Truth Serum: Poisoning Machine Learning Models to Reveal Their Secrets,” Proceedings of the 2022 ACM SIGSAC Conference on Computer and Communications Security, pp. 2779–2792, 2022. https://doi.org/10.1145/3548606.3560554.

20. N. Kandpal, E. Wallace, and C. Raffel, “Deduplicating Training Data Mitigates Privacy Risks in Language Models,” Proceedings of ICML, Proceedings of Machine Learning Research, vol. 162, pp. 10697–10707, 2022. https://proceedings.mlr.press/v162/kandpal22a.html.

21. N. Carlini, D. Paleka, K. D. Dvijotham, T. Steinke, J. Hayase, A. F. Cooper, K. Lee, M. Jagielski, M. Nasr, A. Conmy, E. Wallace, D. Rolnick, and F. Tramèr, “Stealing part of a production language model,” Proceedings of ICML, Proceedings of Machine Learning Research, vol. 235, pp. 5680–5705, 2024. https://proceedings.mlr.press/v235/carlini24a.html.

22. K. Greshake, S. Abdelnabi, S. Mishra, C. Endres, T. Holz, and M. Fritz, “Not What You’ve Signed Up For: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection,” Proceedings of the 16th ACM Workshop on Artificial Intelligence and Security, AISec 2023, 2023. https://doi.org/10.1145/3605764.3623985.

23. A. Zou, Z. Wang, J. Z. Kolter, and M. Fredrikson, “Universal and Transferable Adversarial Attacks on Aligned Language Models,” arXiv:2307.15043v1, July 27, 2023, preprint, 2023. https://arxiv.org/abs/2307.15043v1.

24. X. Liu, N. Xu, M. Chen, and C. Xiao, “AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models,” International Conference on Learning Representations, ICLR 2024, 2024. https://openreview.net/forum?id=7Jwpw4qKkb.

25. E. Debenedetti, J. Zhang, M. Balunović, L. Beurer-Kellner, M. Fischer, and F. Tramèr, “AgentDojo: A Dynamic Environment to Evaluate Prompt Injection Attacks and Defenses for LLM Agents,” Advances in Neural Information Processing Systems, vol. 37, Datasets and Benchmarks Track, 2024, 2024. https://doi.org/10.52202/079017-2636.

26. Q. Zhan, Z. Liang, Z. Ying, and D. Kang, “InjecAgent: Benchmarking Indirect Prompt Injections in Tool-Integrated Large Language Model Agents,” Findings of the Association for Computational Linguistics: ACL 2024, pp. 10471–10506, 2024.

https://doi.org/10.18653/v1/2024.findings-acl.624.

27. S. Toyer, O. Watkins, E. Mendes, J. Svegliato, L. Bailey, T. Wang, I. Ong, K. Elmaaroufi, P. Abbeel, T. Darrell, A. Ritter, and S. Russell, “Tensor Trust: Interpretable Prompt Injection Attacks from an Online Game,” International Conference on Learning Representations, ICLR 2024, 2024.

https://proceedings.iclr.cc/paper_files/paper/2024/hash/519c51529c3544b3430bd8b17d400365-Abstract-Conference.html.

28. Z. Chen, Z. Xiang, C. Xiao, D. Song, and B. Li, “AgentPoison: Red-teaming LLM Agents via Poisoning Memory or Knowledge Bases,” Advances in Neural Information Processing Systems, vol. 37, NeurIPS 2024, 2024. https://doi.org/10.52202/079017-4136.

29. W. Zou, R. Geng, B. Wang, and J. Jia, “PoisonedRAG: Knowledge Corruption Attacks to Retrieval-Augmented Generation of Large Language Models,” 34th USENIX Security Symposium, pp. 3827–3844, 2025.

https://www.usenix.org/conference/usenixsecurity25/presentation/zou-poisonedrag.

30. M. Andriushchenko, F. Croce, and N. Flammarion, “Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks,” International Conference on Learning Representations, ICLR 2025, 2025.

https://proceedings.iclr.cc/paper_files/paper/2025/hash/63fa7efdd3bcf944a4bd6e0ff6a50041-Abstract-Conference.html.

31. M. Nasr, A. Bahramali, and A. Houmansadr, “Defeating DNN-Based Traffic Analysis Systems in Real-Time With Blind Adversarial Perturbations,” 30th USENIX Security Symposium, pp. 2705–2722, 2021. https://www.usenix.org/conference/usenixsecurity21/presentation/nasr.

32. D. Hofer, E. Debenedetti, and F. Tramèr, “Assessing Automated Prompt Injection Attacks in Agentic Environments,” arXiv:2606.10525v1, June 9, 2026, preprint, 2026. https://doi.org/10.48550/arXiv.2606.10525.

33. N. Carlini, M. Jagielski, C. A. Choquette-Choo, D. Paleka, W. Pearce, H. Anderson, A. Terzis, K. Thomas, and F. Tramèr, “Poisoning Web-Scale Training Datasets is Practical,” 2024 IEEE Symposium on Security and Privacy, pp. 407–425, 2024.

https://doi.org/10.1109/SP54263.2024.00179.

34. Y. Chen, Z. Ding, and D. Wagner, “Continuous Learning for Android Malware Detection,” 32nd USENIX Security Symposium, pp. 1127–1144, 2023.

https://www.usenix.org/conference/usenixsecurity23/presentation/chen-yizheng.

35. J. Evertz, N. Risse, N. Neuer, A. Müller, P. Normann, G. Sapia, S. Gupta, D. Pape, S. Shaw, D. Srivastav, C. Wressnegger, E. Quiring, T. Eisenhofer, D. Arp, and L. Schönherr, “Chasing Shadows: Pitfalls in LLM Security Research,” Network and Distributed System Security Symposium, NDSS 2026, Internet Society, 2026. https://www.ndss-symposium.

التنزيلات

منشور

2026-11-08

إصدار

القسم

Articles

كيفية الاقتباس

A Narrative Review of Artificial Intelligence Vulnerabilities in Cybersecurity. (2026). المجلة الدولية للبحوث العلمية, 5(11). https://doi.org/10.59992/IJSR.2026.v5n11p5