The increased attack surface of the sixth generation (6G) network makes old security measures ineffective. In the current paper, the AI-based optimization framework is suggested, combining deep reinforcement learning (DRL) to respond to adaptive threat mitigation and federated learning (FL) to privacy-preserving anomaly detection on distributed 6G nodes. The caching algorithm of query fragment achieves a 34% computation overhead with no associated drop in detection faithfulness. When tested on a 6G Massive IoT dataset and O-RAN simulation, the framework has a 97.8% detection rate against DDoS attacks, data injection attacks, and adversarial evasion attacks. Compared to current AI-based intrusion detection systems, it reduces false positives by 42 percent and shortens response time by 58 percent. Findings affirm that next generation wireless infrastructures require adaptive, intelligent security.
Naga Naveena Chennupati· 2026 7th International Confe...· 0 citations
The integration of IoT into smart cities exposes serious cyber security risks, which old centralized designs would fail to combat. In this paper, the model suggests a unified system that would use AI and block chain technology to protect smart city IoT systems. A lightweight hybrid CNN-LSTM model is used to detect anomalies in real-time at the edge nodes and federated learning with differential privacy can be used to train collaboratively without exposing raw data. Permissioned block chain layer provides tamper-proof records and decentralized management of trust. A query fragment caching algorithm is a resource-optimal query strategy to block chain queries. CIC-IDS2017 and BoT-IoT datasets analysis show 98.6% detection, 97.5% F1-score, 134.6 ms latency, and 2,615 transactions-per-second, and 41% less energy usage than un cached block chain access. The framework is more effective than the current methods in all measures.
Their combination of adversarial AI attacks with cryptographically relevant quantum computers endangers the traditional public-key infrastructure. This paper proposes a hybrid system that combines real-time deep learning-based threat detection and Quantum Key Distribution (QKD) to secure communication systems. A convolutional neural network with attention mechanism detects network anomalies with 98.4% accuracy on the CIC-IDS-2017 dataset. At the same time, a decoy-state BB84 QKD protocol is used to create symmetric keys on a modeled 40 km fiber channel with a quantum bit error rate of less than 2.5%. A new query fragment caching algorithm cuts the key delivery latency by a factor of 37. Empirical evidence demonstrates the system throughput of 850 Mbps and key generation rate of 12.4 kbps providing a viable roadmap to information-theoretically secure communication when using active cyber threats.
Naga Naveena Chennupati· International Conference Com...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
