⚠ Official Notice: www.ijisrt.com is the official website of the International Journal of Innovative Science and Research Technology (IJISRT) Journal for research paper submission and publication. Please beware of fake or duplicate websites using the IJISRT name.



Deep Reinforcement Learning for Mitigating Selective Forwarding Attacks in ACO


Authors : Ibrahim Samson Salifu; Gaddafi Abdul-Salaam

Volume/Issue : Volume 11 - 2026, Issue 10 - October


Google Scholar : https://tinyurl.com/ypbt9bjh

DOI : https://doi.org/10.38124/ijisrt/26Oct1627

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.


Abstract : Wireless Sensor Networks (WSNs) and Internet of Things (IoT) networks rely on resourceconstrained devices and unstable wireless links, making them vulnerable to selective forwarding attacks. Conventional routing methods often prioritise delay, energy and link quality, so a route may remain attractive even when a compromised node drops some packets while forwarding others. This study designed and evaluated a DQN-supported, evidence-gated security mechanism for mitigating selective forwarding attacks in Ant Colony Optimisation (ACO) routing, implemented as the Adaptive Bioinspired Routing Framework (ABRF). The DQN was trained offline on synthetic node-state transitions and, during simulation, used live routing observations to propose one of five graded actions. The evidence gate validated each proposed action using forwarding and route-advertisement evidence before the action modified pheromone or route preference. Evaluation was conducted in a Python discrete-event simulator using smart-home, smart-traffic and wearable-IoT scenarios. The main experiment included 2,250 attack runs and 450 clean-control runs and compared ABRF with simplified RPL-like, AODV-like, ACO-only and traditional-IDS baselines. ABRF achieved a mean attack-step detection rate of 0.847, a hard false-action rate of 0.033 and a packet delivery ratio of 0.665, compared with 0.681, 0.126 and 0.579 for the traditional IDS. Its soft false-action rate was 0.312, indicating that cautious pheromone reductions occurred more often than hard isolation. Dynamic INT8 quantisation reduced the model file size by about 60 percent, although inference was tested on a Colab CPU rather than physical IoT hardware.The findings show that validated DRL security actions can mitigate selective forwarding by directly influencing ACO pheromone decisions while supporting secure route selection under the tested simulation conditions. The conclusions remain limited by the purpose-built simulator, simplified baselines and offline-trained policy.

Keywords : Ant Colony Optimisation, Deep Q-Network, Deep Reinforcement Learning, Evidence-Gated Routing, Selective Forwarding Attack, Internet of Things, Wireless Sensor Networks.

References :

  1. Alfriehat, N., Anbar, M., Aladaileh, M., Hasbullah, I. H., Shurbaji, T. A., Karuppayah, S. and Almomani, A. (2024). RPL-based attack detection approaches in IoT networks: Review and taxonomy. Artificial Intelligence Review, 57, 248.
  2. Alansari, Z., Anuar, N. B., Kamsin, A. and Belgaum, M. R. (2023). RPLAD3: anomaly detection of blackhole, grayhole, and selective forwarding attacks in wireless sensor network-based Internet of Things. PeerJ Computer Science, 9, e1309.
  3. Bala, K., Venu, D., Dudi, B. P., Nirmala, V., Ashok Kumar, K. and Manohara, M. (2026). Federated deep reinforcement Q-learning for secure and energy-efficient data routing in Internet of Things networks. Peer-to-Peer Networking and Applications, 19, 88.
  4. Cevallos Moreno, J. F., Rizzardi, A., Sicari, S. and Coen-Porisini, A. (2023). Deep reinforcement learning for intrusion detection in Internet of Things: Best practices, lessons learnt, and open challenges. Computer Networks, 236, 110016.
  5. Dorigo, M. and Stützle, T. (2004). Ant Colony Optimization. Cambridge, MA: MIT Press.
  6. Dubey, G. P., Stalin, S., Alqahtani, O., Alasiry, A., Sharma, M., Aleryani, A., Shukla, P. K. and Alouane, M. T.-H. (2023). Optimal path selection using reinforcement learning based ant colony optimization algorithm in IoT-based wireless sensor networks with 5G technology. Computer Communications, 212, 377-389.
  7. Fu, T., Hao, S., Chen, Q., Yan, Z., Liu, H. and Rezaeipanah, A. (2024). An energy-aware secure routing scheme in Internet of Things networks via two-way trust evaluation. Pervasive and Mobile Computing, 105, 101995.
  8. Han, H., Tang, J. and Jing, Z. (2024). Wireless sensor network routing optimisation based on improved ant colony algorithm in the Internet of Things. Heliyon, 10(1), e23577.
  9. Jamshidi, S., Nikanjam, A., Wazed Nafi, K., Khomh, F. and Rasta, R. (2025). Application of deep reinforcement learning for intrusion detection in Internet of Things: A systematic review. Internet of Things, 31, 101531.
  10. Kandhoul, N. and Dhurandher, S. K. (2022). Deep Q learning based secure routing approach for OppIoT networks. Internet of Things, 20, 100597.
  11. Liu, Z., Rong, J., Jiang, Y. and Zhang, L. (2023). Satellite network security routing technology based on deep learning and trust management. Sensors, 23(20), 8474.
  12. Mahjoub, C., Hamdi, M., Alkanhel, R. I., Mohamed, S. and Ejbali, R. (2024). An adversarial environment reinforcement learning-driven intrusion detection algorithm for Internet of Things. EURASIP Journal on Wireless Communications and Networking, 2024, 21.
  13. Mnih, V., Kavukcuoglu, K., Silver, D. et al. (2015). Human-level control through deep reinforcement learning. Nature, 518, 529-533.
  14. Omar, A. A. R. A., Soudan, B. and Altaweel, A. (2024). UOS_IOTSH_2024: A comprehensive network traffic dataset for sinkhole attacks in diverse RPL IoT networks. Data in Brief, 55, 110650.
  15. Perkins, C., Belding-Royer, E. and Das, S. (2003). Ad hoc On-Demand Distance Vector (AODV) Routing. RFC 3561.
  16. Pidy Pidy, C., Moskolaï Ngossaha, J., Tchappi, I. and Bowong Tsakou, J. (2026). CARAC-MDRL: Cluster-based ant-colony routing with adaptive cluster head and multi-agent deep reinforcement learning. Procedia Computer Science, 280, 163-170.
  17. Sharmin, A., Olanrewaju, R. F., Khan, B. U. I., Anwar, F., Motakabber, S. M. A., Rosely, N. F. L. M. and Hashim, A. H. A. (2023). Secure IoT routing through manifold criterion trust evaluation using ant colony optimization. International Journal of Advanced Computer Science and Applications, 14(11), 131-143.
  18. Tawfeek, M. A., Alrashdi, I., Alruwaili, M., Jamel, L., Elhady, G. F. and Elwahsh, H. (2025). Improving energy efficiency and routing reliability in wireless sensor networks using modified ant colony optimization. EURASIP Journal on Wireless Communications and Networking, 2025, 22.
  19. Wang, Y., Li, Y., Lei, J. and Shang, F. (2024). Robust and energy-efficient RPL optimization algorithm with scalable deep reinforcement learning for IIoT. Computer Networks, 255, 110894.
  20. Winter, T., Thubert, P., Brandt, A., Hui, J., Kelsey, R., Levis, P., Pister, K., Struik, R., Vasseur, J. P. and Alexander, R. (2012). RPL: IPv6 Routing Protocol for Low-Power and Lossy Networks. RFC 6550.
  21. Zaminkar, M. and Fotohi, R. (2020). SoS-RPL: Securing Internet of Things against sinkhole attack using RPL protocol-based node rating and ranking mechanism. Wireless Personal Communications, 114, 1287-1312.

Wireless Sensor Networks (WSNs) and Internet of Things (IoT) networks rely on resourceconstrained devices and unstable wireless links, making them vulnerable to selective forwarding attacks. Conventional routing methods often prioritise delay, energy and link quality, so a route may remain attractive even when a compromised node drops some packets while forwarding others. This study designed and evaluated a DQN-supported, evidence-gated security mechanism for mitigating selective forwarding attacks in Ant Colony Optimisation (ACO) routing, implemented as the Adaptive Bioinspired Routing Framework (ABRF). The DQN was trained offline on synthetic node-state transitions and, during simulation, used live routing observations to propose one of five graded actions. The evidence gate validated each proposed action using forwarding and route-advertisement evidence before the action modified pheromone or route preference. Evaluation was conducted in a Python discrete-event simulator using smart-home, smart-traffic and wearable-IoT scenarios. The main experiment included 2,250 attack runs and 450 clean-control runs and compared ABRF with simplified RPL-like, AODV-like, ACO-only and traditional-IDS baselines. ABRF achieved a mean attack-step detection rate of 0.847, a hard false-action rate of 0.033 and a packet delivery ratio of 0.665, compared with 0.681, 0.126 and 0.579 for the traditional IDS. Its soft false-action rate was 0.312, indicating that cautious pheromone reductions occurred more often than hard isolation. Dynamic INT8 quantisation reduced the model file size by about 60 percent, although inference was tested on a Colab CPU rather than physical IoT hardware.The findings show that validated DRL security actions can mitigate selective forwarding by directly influencing ACO pheromone decisions while supporting secure route selection under the tested simulation conditions. The conclusions remain limited by the purpose-built simulator, simplified baselines and offline-trained policy.

Keywords : Ant Colony Optimisation, Deep Q-Network, Deep Reinforcement Learning, Evidence-Gated Routing, Selective Forwarding Attack, Internet of Things, Wireless Sensor Networks.

Paper Submission Last Date
30 - November - 2026

SUBMIT YOUR PAPER CALL FOR PAPERS
Video Explanation for Published paper

Never miss an update from Papermashup

Get notified about the latest tutorials and downloads.

Subscribe by Email

Get alerts directly into your inbox after each post and stay updated.
Subscribe
OR

Subscribe by RSS

Add our RSS to your feedreader to get regular updates from us.
Subscribe