cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Andri Putra Kesmawan
Contact Email
journal@idpublishing.org
Phone
+6281990251989
Journal Mail Official
journal@idpublishing.org
Editorial Address
Perumahan Sidorejo, Jl. Sidorejo Gg. Sadewa No.D3, Sonopakis Kidul, Ngestiharjo, Kapanewon Kasihan, Kabupaten Bantul, Daerah Istimewa Yogyakarta 55182
Location
Kab. bantul,
Daerah istimewa yogyakarta
INDONESIA
Journal of Technology and System Information
Published by Indonesian Journal Publisher
ISSN : -     EISSN : 30322081     DOI : https://doi.org/10.47134/jtsi
Core Subject : Science,
Computer Science & IT
The Journal of Technology and System Information is dedicated to publishing cutting-edge research and advancements in the broad and dynamic intersection of technology and information systems. The focus of the journal is to facilitate the exchange of knowledge and ideas in these interconnected domains, fostering a deeper understanding of the role of technology in shaping information systems and vice versa. The journal welcomes contributions that span theoretical, empirical, and practical aspects, with an emphasis on the transformative impact of technology on information systems and vice versa. The scope of JTSI is a Information Technology and Systems, Data Management and Analytics, Emerging Technologies, System Design and Optimization, Cybersecurity and Privacy, Networks and Communication Systems, Artificial Intelligence and Machine Learning, Human-Computer Interaction.
Arjuna Subject : Ilmu Komputer (semua kategori) - Ilmu Komputer (Lain-Lain)
Articles 72 Documents
 4   5   6   7   8 
AdverShield-LLM: Adversarial Robustness Certification for IoT-Integrated Retrieval-Augmented Generation via Randomized Smoothing Yasser Samir Hadi
Journal of Technology and System Information Vol. 3 No. 2 (2026): April
Publisher : Indonesian Journal Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47134/jtsi.v3i2.6047

Abstract

The emergence of the Internet of Things (IoT) ecosystems, Retrieval-Augmented Generation (RAG) systems have become commonplace and provide a means for embedding dynamically retrieved external knowledge in the response from a Large Language Model (LLM). While potentially helpful, IoT-enabled RAG pipelines present significant adversarial threats such as poisoning passages into the IoT knowledge base, altering dense retrieval embeddings, and conducting indirect prompt injection attacks via the inputs through the IoT sensors, all of which can impact the fidelity of generated responses and compromise the trustworthiness of the system. Current defenses are based mostly on heuristic filtering or empirical adversarial training, and are not known to be robustly certified or are fragile under adaptive adversaries. In response to these challenges, this article introduces a new certified defense framework named AdverShield-LLM to combine the randomized smoothing technique with a multi-granular noise injection mechanism well-suited to the distributed and low latency requirements of RAG systems in the IoT domain. AdverShield-LLM consists of three synergistic modules: (i) Passage-Level Smoothed Aggregation (PLSA) module which certifies the robustness of RAG retrieval against bounded corpus poisoning under an isolate-then-smooth paradigm, (ii) Token-Adaptive Gaussian Defense (TAGD) layer that certifies LLM generation against indirect prompt injection by propagating l_2-norm perturbation bounds through the transformer attention stack, and (iii) IoT-Aware Certified Radius Scheduler (IACRS) that dynamically schedules noise budgets among constrained edge nodes while preserving the certified radius. AdverShield-LLM is evaluated on three IoT security benchmarks—MS-RAG-IoT, NQ-Adversarial and IoTQA-Poison—with extensive experiments showing its certified accuracy is 81.4% under l_2 perturbation radius σ=0.50 compared to the strongest baseline RobustRAG which reported +9.3% accuracy, and reduced the attack success rate from 74.2% to 8.6% against PoisonedRAG. Moreover, AdverShield-LLM ensures the accuracy of clean answers within 2.1% of the undefended RAG accuracy, proving that certified robustness does not compromise the utility of RAGs in resource-limited IoT environments.
Performance Improvement of f-OFDM Systems Using a Concatenated RS/LDPC Coding Scheme Ghasan Ali Hussain
Journal of Technology and System Information Vol. 3 No. 2 (2026): April
Publisher : Indonesian Journal Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47134/jtsi.v3i2.6091

Abstract

In wireless communication systems, transmission errors are inevitably generated due to interference and fading. Therefore, various approaches have been developed to enhance system reliability, including increasing the transmitted signal power and utilizing error detection and correction schemes. Among these approaches, channel coding is an important technique for reducing the Bit Error Rate (BER). Although LDPC codes are widely adopted in 5G wireless communication systems; achieving ultra-low BER values remains challenging in LDPC codes due to the error-floor phenomenon. To address this limitation, a modified concatenated RS/LDPC code is proposed for an f-OFDM system in this paper. It employs RS codes with LDPC codes followed by an interleaver. Unlike the conventional concatenated RS/LDPC codes that separated both codes by an interleaver. Simulation results demonstrate that the suggested system achieves superior BER performance compared with the conventional concatenated scheme and standalone RS and LDPC codes under both BPSK and QPSK. Furthermore, the suggested f-OFDM system provides superior Out-of-Band Emission (OOBE) suppression compared with the conventional OFDM system, while maintaining a Peak-to-Average Power Ratio (PAPR) performance comparable to that of the conventional OFDM system. Based on the results, the suggested f-OFDM system is considered a promising candidate for 5G and beyond systems.

Page 8 of 8 | Total Record : 72

 4   5   6   7   8 

Filter by Year

2024 2026


Reset
Filter By Issues
All Issue Vol. 3 No. 2 (2026): April Vol. 3 No. 1 (2026): January Vol. 2 No. 4 (2025): October Vol. 2 No. 3 (2025): July Vol. 2 No. 2 (2025): April Vol. 2 No. 1 (2025): January Vol. 1 No. 4 (2024): October Vol. 1 No. 3 (2024): July Vol. 1 No. 2 (2024): April Vol. 1 No. 1 (2024): January