Presentation Details
  1. Home
  2. Presentation List
  3. Presentation Details
Trust-Aware Hybrid CTDE for Anti-Jamming UAV Relay Swarms Under Gray-Hole Attacks
ID：20 View Protection：ATTENDEE Updated Time：2026-10-04 23:17:16 Hits：78 In-person

Start Time：2026-10-13 17:00（Asia/Ho_Chi_Minh）

Duration：15min

Session：S3 Track 3: Privacy, Security for Networks » S3-2Track 3: Privacy, Security for Networks

Presentation File Attachment File

Tips: Only the registered participant can access the file. Please sign in first.

Abstract
Abstract—Unmanned aerial vehicle (UAV) relay swarms can
maintain connectivity when terrestrial infrastructure is unavail
able, but their open wireless links expose them to both external
jamming and internal packet-forwarding attacks. This paper
develops a trust-aware, hybrid centralized-training decentralized
execution (CTDE) architecture for a 10-UAV swarm serving 10
source–destination (SU–DU) pairs over two-hop links within a
120 m × 120 m tactical area in the presence of two external jam
mers and an identity-hidden gray-hole UAV. The compromised
UAV follows the legitimate mobility and power-control policy,
but after a dormant period selectively drops forwarded packets
with probability 0.2, 0.5, or 0.8. Its identity is hidden from the
learned policy and the network controller. Each UAV applies a
parameter-shared Double Deep Q-Network (Double-DQN) over a
53-dimensional local observation to select one of 21 joint motion–
power actions, while a centralized critic uses a 90-dimensional
global state for advantage shaping. A channel-calibrated trust
controller uses trusted packet-observation points, rather than
relay-reported counters, to isolate suspicious relays and reassign
traffic. We report scheduled Shannon throughput (in Mbit/s) and
ACK-confirmed packet goodput (in kbit/s) as distinct metrics.
The reported results are preliminary point estimates from one
1.2-million-step training run (seed 42, initialized from compatible
legacy weights) and one 500-slot rollout per attack severity; they
do not establish statistical significance. In these runs, scheduled
throughput is approximately 0.6–1.0 Mbit/s across the swarm.
At 50% and 80% packet dropping, the trust controller detects
the attacker within 4 and 3 slots, respectively, and the observed
packet-delivery ratios exceed the no-defense point estimates by
7.2 and 7.1 percentage points.
Index Terms—UAV swarm, anti-jamming, gray-hole attack,
selective forwarding, trust management, centralized training,
Double-DQN, relay reassignment.
Keywords
Deep Q Learning,Machine learning model,deep learning; K-means clustering algorithm; power system; wind power ramping; severity grading
Speaker
Trung Kien Quan
student VNU - University of Engineering and Technology

Submission Author
Trung Kien Quan VNU - University of Engineering and Technology
Minh Tien Ha VNU - University of Engineering and Technology
Thai Duong Nguyen VNU - University of Engineering and Technology
Ngoc-Tan Nguyen VNU - University of Engineering and Technology
Submit Comment
Verify Code Change Another
All Comments
Important Date

  • Conference Date

    Oct 11

    2026

    to

    Oct 14

    2026

  • Dec 30 2025

    Contribution Submission Deadline

  • Sep 28 2026

    Early Bird Registration

  • Oct 14 2026

    Draft paper submission deadline

  • Oct 15 2026

    Registration deadline

Sponsored By
United Societies of Science
Organized By
Posts and Telecommunications Institute of Technology
Supported By
IEEE Section
IEEE Vietnam Section
Contact Information
Login to view full contact details