Many industries have changed due to the quick spread of IoT devices, which have improved efficiency and connectedness. But this increase has also brought up serious security flaws, which makes IoT networks a prime target for hackers. The creation of AI-powered intrusion detection systems (IDS) designed especially for Internet of Things contexts is examined in this overview of the literature. These systems may examine enormous volumes of data produced by IoT devices by utilizing machine learning algorithms, spotting unusual patterns that may point to security breaches. The paper evaluates the efficacy of current machine learning methods in real-time anomaly detection and response by classifying them into supervised, unsupervised, and reinforcement learning approaches. Along with cutting-edge strategies like feature selection and hybrid models to improve detection accuracy with the least amount of resources, the main challenges such as computational and energy limitations are also covered. In the end, this assessment emphasizes the need for a system of many levels of protection that not only address current threats but also anticipate challenges posed by evolving cyberattacks techniques. By combining knowledge from current research, the results hope to guide the development of more resilient and flexible AI-powered intrusion detection systems, assisting in the safe deployment of IoT networks for a range of applications.
INTERNET OF THINGS (IOT) NETWORKS: AI-POWERED SECURE INTRUSION DETECTION
Bora Suri,V. Reddy,S. Srinivasan
Published 2025 in International Journal of Applied Mathematics
ABSTRACT
PUBLICATION RECORD
- Publication year
2025
- Venue
International Journal of Applied Mathematics
- Publication date
2025-11-03
- Fields of study
Not labeled
- Identifiers
- External record
- Source metadata
Semantic Scholar
CITATION MAP
EXTRACTION MAP
CLAIMS
- No claims are published for this paper.
CONCEPTS
- No concepts are published for this paper.
REFERENCES
Showing 1-83 of 83 references · Page 1 of 1
CITED BY
- No citing papers are available for this paper.
Showing 0-0 of 0 citing papers · Page 1 of 1