Paper Title
PROACTIVE CYBERSECURITY FOR ENTERPRISE APIS: LEVERAGING AI-DRIVEN INTRUSION DETECTION SYSTEMS IN DISTRIBUTED JAVA ENVIRONMENTS
Keywords
- api security
- intrusion detection systems
- microservices architecture
- machine learning
- distributed systems
- spring boot
- cybersecurity
Publication Info
Volume: 5 | Issue: 1 | Pages: 34-52
Published On
February, 2024
Downloads
FULL PDF
Abstract
Enterprise APIs in distributed Java environments face unprecedented cybersecurity challenges as microservice architectures expand attack surfaces beyond traditional perimeter defenses. Conventional intrusion detection systems (IDS) fail to address API-specific threats such as authentication bypass, request manipulation, and behavioral anomalies in real-time distributed systems. This paper presents a novel AI-driven intrusion detection framework specifically designed for Spring Boot-based microservices using unsupervised learning algorithms and distributed tracing correlation. The proposed system integrates autoencoder neural networks with API gateway telemetry, achieving 92% detection accuracy with minimal latency overhead of less than 10ms per request. Through comprehensive evaluation across financial and insurance platforms, our solution demonstrates superior performance in detecting sophisticated API-level attacks including token abuse, privilege escalation, and distributed denial-of-service patterns. The framework leverages Zipkin for distributed tracing, Logstash for event aggregation, and a custom Spring Boot interceptor pattern for real-time threat mitigation. Results indicate significant improvements in proactive threat detection while maintaining enterprise-grade scalability and operational efficiency.
View more »