Evaluating Adversarial Attacks Against Artificial Intelligence Systems in Application Deployments
ABSTRACT Businesses have invested billions into artificial intelligence (AI) applications, leading to a sharp rise in the number of AI applications being released to customers. Taking into account previous approaches to attacking machine learning models, we conduct a comparative analysis of adversar...
Saved in:
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2025-04-01
|
| Series: | Applied AI Letters |
| Subjects: | |
| Online Access: | https://doi.org/10.1002/ail2.121 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850127330635153408 |
|---|---|
| author | Lera Leonteva |
| author_facet | Lera Leonteva |
| author_sort | Lera Leonteva |
| collection | DOAJ |
| description | ABSTRACT Businesses have invested billions into artificial intelligence (AI) applications, leading to a sharp rise in the number of AI applications being released to customers. Taking into account previous approaches to attacking machine learning models, we conduct a comparative analysis of adversarial attacks, contrasting large language models (LLMs) being deployed through application programming interfaces (APIs) with the same attacks against locally deployed models to evaluate the significance of security controls in production deployments on attack success in black‐box environments. The article puts forward adversarial attacks that are adapted for remote model endpoints in order to create a threat model that can be used by security organizations to prioritize controls when deploying AI systems through APIs. This paper contributes: (1) a public repository of adversarial attacks adapted to handle remote models on https://github.com/l3ra/adversarial‐ai, (2) benchmarking results of remote attacks comparing the effectiveness of attacks on remote models with those on local models, and (3) a framework for assessing future AI system deployment controls. By providing a practical framework for benchmarking the security of remote AI systems, this study contributes to the understanding of adversarial attacks in the context of natural language processing models deployed by production applications. |
| format | Article |
| id | doaj-art-72a73cd4c0a846b1a2ffd625be2cf22c |
| institution | OA Journals |
| issn | 2689-5595 |
| language | English |
| publishDate | 2025-04-01 |
| publisher | Wiley |
| record_format | Article |
| series | Applied AI Letters |
| spelling | doaj-art-72a73cd4c0a846b1a2ffd625be2cf22c2025-08-20T02:33:43ZengWileyApplied AI Letters2689-55952025-04-0162n/an/a10.1002/ail2.121Evaluating Adversarial Attacks Against Artificial Intelligence Systems in Application DeploymentsLera Leonteva0Leo AI London UKABSTRACT Businesses have invested billions into artificial intelligence (AI) applications, leading to a sharp rise in the number of AI applications being released to customers. Taking into account previous approaches to attacking machine learning models, we conduct a comparative analysis of adversarial attacks, contrasting large language models (LLMs) being deployed through application programming interfaces (APIs) with the same attacks against locally deployed models to evaluate the significance of security controls in production deployments on attack success in black‐box environments. The article puts forward adversarial attacks that are adapted for remote model endpoints in order to create a threat model that can be used by security organizations to prioritize controls when deploying AI systems through APIs. This paper contributes: (1) a public repository of adversarial attacks adapted to handle remote models on https://github.com/l3ra/adversarial‐ai, (2) benchmarking results of remote attacks comparing the effectiveness of attacks on remote models with those on local models, and (3) a framework for assessing future AI system deployment controls. By providing a practical framework for benchmarking the security of remote AI systems, this study contributes to the understanding of adversarial attacks in the context of natural language processing models deployed by production applications.https://doi.org/10.1002/ail2.121adversarial attacksapplication programming interfaces (APIs)artificial intelligencecloud securitycyber securitylarge language models (LLMs) |
| spellingShingle | Lera Leonteva Evaluating Adversarial Attacks Against Artificial Intelligence Systems in Application Deployments Applied AI Letters adversarial attacks application programming interfaces (APIs) artificial intelligence cloud security cyber security large language models (LLMs) |
| title | Evaluating Adversarial Attacks Against Artificial Intelligence Systems in Application Deployments |
| title_full | Evaluating Adversarial Attacks Against Artificial Intelligence Systems in Application Deployments |
| title_fullStr | Evaluating Adversarial Attacks Against Artificial Intelligence Systems in Application Deployments |
| title_full_unstemmed | Evaluating Adversarial Attacks Against Artificial Intelligence Systems in Application Deployments |
| title_short | Evaluating Adversarial Attacks Against Artificial Intelligence Systems in Application Deployments |
| title_sort | evaluating adversarial attacks against artificial intelligence systems in application deployments |
| topic | adversarial attacks application programming interfaces (APIs) artificial intelligence cloud security cyber security large language models (LLMs) |
| url | https://doi.org/10.1002/ail2.121 |
| work_keys_str_mv | AT leraleonteva evaluatingadversarialattacksagainstartificialintelligencesystemsinapplicationdeployments |