Adversarial Attacks and Defenses in AI Systems: Challenges, Strategies, and Future Directions

Lawrence Samuel Igenewari and Onyemaechi Emmanuel Okoh
Additional contact information
Lawrence Samuel Igenewari: Department of Computer Science Ignatius Ajuru University of Education Rumuolumeni Port Harcourt, Nigeria Nnamdi Azikiwe University Awka, Nigeria
Onyemaechi Emmanuel Okoh: Department of Computer Science Ignatius Ajuru University of Education Rumuolumeni Port Harcourt, Nigeria Nnamdi Azikiwe University Awka, Nigeria

International Journal of Research and Innovation in Applied Science, 2025, vol. 10, issue 6, 996-1022

Abstract: AI systems are vulnerable to adversarial manipulations (Szegedy et al., 2014). These attacks exploit model weaknesses through subtle input perturbations (Carlini & Wagner, 2017), risking safety in applications like facial recognition and autonomous driving (Eykholt et al., 2018). Defense mechanisms, including adversarial training (Madry et al., 2018) and input preprocessing (Guo et al., 2018), often face trade-offs between robustness and efficiency.

Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
https://www.rsisinternational.org/journals/ijrias/ ... issue-6/996-1022.pdf (application/pdf)
https://rsisinternational.org/journals/ijrias/arti ... d-future-directions/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:bjf:journl:v:10:y:2025:i:6:p:996-1022

Access Statistics for this article

International Journal of Research and Innovation in Applied Science is currently edited by Dr. Renu Malsaria

More articles in International Journal of Research and Innovation in Applied Science from International Journal of Research and Innovation in Applied Science (IJRIAS)
Bibliographic data for series maintained by Dr. Renu Malsaria ().