Cited by 13Wireless Communication Security TechniquesAdvanced Wireless Communication TechnologiesIoT and Edge/Fog Computing

Terahertz-Based IRS-Assisted Secure Symbiotic Radio Communication: A DRL Approach

Open access
Shahwar, Muhammad, Ahmed, Manzoor, Hussain, Touseef, Ahmad, Sajed, Ullah Khan, Wali, Sheraz, Muhammad, Chee Chuah, Teong·2025·IEEE Access

Abstract

Developing wireless communication technologies is essential to satisfy the requirements of new applications and the increasing proliferation of interconnected devices. This research presents a resilient terahertz (THz)-based secure transmission framework for an active intelligent reflecting surface (IRS)-enabled symbiotic radio (SR) system in the presence of multiple eavesdroppers (Eves). The IRS facilitates secure transmission for the primary transmitter (PT) by intelligently adjusting the phase shifts of the signals from the PT, while simultaneously transmitting its own data to an Internet of Things (IoT) device. In light of the existence of numerous eves and unpredictable channels in real-world situations, we concurrently optimize the active beamforming of the PT and the phase shifts of the IRS to enhance the secrecy of IRS-assisted secure relay networks while adhering to quality-of-service standards and secure communication rates. To address this intricate non-convex stochastic optimization issue, we propose a secure beamforming technique named DDPG-SR, utilizing an effective deep reinforcement learning (DRL)-based deep deterministic policy gradient (DDPG) scheme to determine the optimal beamforming approach against Eves. This method seeks to establish an optimal beamforming strategy to counteract Eves under dynamic environmental circumstances. Comprehensive simulation experiments confirm the effectiveness of our proposed solution, showcasing enhanced performance relative to conventional IRS methods, IRS backscattering-based anti-evesdropping techniques, and other benchmark tactics for secrecy performance.

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1109/access.2025.3539088

Cites

39 of 39 references verified0 citation errors · 0 not checkable

Statistics

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • The legal position of DRLs varies; in the UK, they facilitate adherence to regulatory mandates under IR(ME)R, but in Japan and Saudi Arabia, they are only advisory.

    “Moreover, the legal position of DRLs varies; in the UK, they facilitate adherence to regulatory mandates under IR(ME)R,117 but in Japan and Saudi Arabia, they are only advisory.”

    From Computed Tomography Diagnostic Reference Levels Worldwide and in Jordan: Implications for Patient Dose Reduction (2026) · cites this paper as [117]

    The paper’s index terms (p. 1) use DRL to mean deep reinforcement learning, and its algorithm-design section (p. 7) discusses wireless beamforming. Searches for IR(ME)R, diagnostic reference levels, and the named countries found no passage addressing their legal status. (LLM, conf=0.78)

    Experimental — accuracy not yet measured

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Cites

Part of this paper’s reference list could not be split into single entries.

Flagged first, then by citations

Cited by

Sorted by citations

Authors
Shahwar, M., Ahmed, M., Hussain, T., Ahmad, S., Ullah Khan, W., Sheraz, M., & Chee Chuah, T.
Affiliations
  • Qingdao University (CN)
  • Hubei Engineering University (CN)
  • Beijing University of Posts and Telecommunications (CN)
  • Interdisciplinary Centre for Security, Reliability and Trust (SnT), University of Luxembourg, Esch-sur-Alzette, Luxembourg
  • Multimedia University (MY)
  • Faculty of Engineering, Multimedia University, Cyberjaya, Selangor, Malaysia
Venue
IEEE Access
Published
2025
Volume
13
Pages
24014-24027
ISSN
2169-3536 (ISSN-L)
OpenAlex
W4407168446
Cited by
11
References
39
Citations by year
2026: 6 · 2025: 5
FWCI
2.47
Type
journal article
Language
en
Open access
Locations
  • IEEE Access (publishedVersion, cc-by-nc-nd)
  • Siti Hasmah Digital Library-MMU Institutiona Repository (Multimedia University) (acceptedVersion)
  • Open Repository and Bibliography (University of Luxembourg) (submittedVersion, cc-by-nc-nd)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
  • OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information) (submittedVersion)
Funders
  • Multimedia University (MMUI/240021)
  • Telekom Research and Development Sdn Bhd (RDTC/241149)
Topics
  • Physical Sciences › Engineering › Electrical and Electronic Engineering › Wireless Communication Security Techniques
  • Physical Sciences › Engineering › Electrical and Electronic Engineering › Advanced Wireless Communication Technologies
  • Physical Sciences › Computer Science › Computer Networks and Communications › IoT and Edge/Fog Computing
Keywords
terahertz communication, reconfigurable intelligent surface, symbiotic radio, physical layer security, eavesdropper, deep deterministic policy gradient, deep reinforcement learning, beamforming optimization, phase shift optimization, secrecy rate, Internet of Things

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review