ETRI Journal最新文献

{"title":"SF-CAMNet: A spatial–frequency fusion network for robust spatial-domain image steganalysis","authors":"Mehnaz Batool,&nbsp;Adil Bashir","doi":"10.4218/etrij.2026-0036","DOIUrl":"https://doi.org/10.4218/etrij.2026-0036","url":null,"abstract":"<p>Spatial domain image steganalysis has become increasingly important due to the widespread use of digital images for communication and data sharing over the internet and social media. While steganography enables secure communication and digital watermarking, it can also be exploited for malicious purposes, making reliable detection essential. This study proposes SF-CAMNet, a deep learning framework for spatial-domain image steganalysis that integrates spatial and frequency-domain features. The model combines Spatial Rich Model (SRM) filters, the Convolutional Block Attention Module (CBAM), Mish activation, and a Discrete Wavelet Transform (DWT) branch to enhance the detection of subtle embedding artifacts. Performance was evaluated on the BOSSBase v1.01 dataset using S-UNIWARD, WOW, HILL, HUGO, and MiPOD at payloads of 0.2 and 0.4 bpp. Cross-dataset evaluation on the BOWS2 dataset further demonstrates the robustness and generalization capability of the proposed model. Experimental results show that SF-CAMNet achieves competitive performance compared with state-of-the-art spatial-domain image steganalysis methods.</p>","PeriodicalId":11901,"journal":{"name":"ETRI Journal","volume":"48 5","pages":"820-837"},"PeriodicalIF":2.0,"publicationDate":"2026-10-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.4218/etrij.2026-0036","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149222796","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Special issue on trustworthy and safe AI: Interpretability, robustness, and security","authors":"Sungwon Yi,&nbsp;Dae Hun Nyang,&nbsp;Jaehyung Kim,&nbsp;Jaegul Choo,&nbsp;Daeseon Choi,&nbsp;Soonmin Hwang","doi":"10.4218/etr2.70162","DOIUrl":"https://doi.org/10.4218/etr2.70162","url":null,"abstract":"&lt;p&gt;Recent advances in artificial intelligence (AI), particularly in large language models (LLMs) and physical robotics, have rapidly reshaped daily life and industrial applications. As these systems become more capable and autonomous, ensuring their safety, trustworthiness, robustness, and alignment with human values has become increasingly important. In response to these challenges, this special issue on “Trustworthy and Safe AI: Interpretability, Robustness, and Security” brings together recent research that advances the safety and trustworthiness of AI across diverse models, systems, and real-world applications.&lt;/p&gt;&lt;p&gt;This special issue received 50 submissions, reflecting the growing research interest in trustworthy and safe AI. Following a rigorous peer-review process, 11 papers were selected for publication. Together, these studies span several interconnected dimensions of the field, ranging from emerging security threats in LLMs and multi-agent systems to robustness, autonomous system safety, and explainability for practical deployment.&lt;/p&gt;&lt;p&gt;The following five papers focus on emerging security and safety threats across modern AI systems. These studies examine how vulnerabilities arise from adversarial attacks, multi-agent interactions, social context, multilingual settings, and hidden information while exploring the corresponding mechanisms for detection and defense.&lt;/p&gt;&lt;p&gt;In [&lt;span&gt;1&lt;/span&gt;], the authors investigate a more evasive mixed clean/dirty-label X-to-X backdoor attack and propose an ensemble defense that combines complementary detectors such as Neural Cleanse, PT-RED, CEPA, and MMBD. This work is significant because it addresses both robustness and interpretability, and the ensemble improves resilience across diverse backdoor mechanisms while also supporting trigger inversion to help explain the nature of the detected attack. By jointly considering stronger adversarial attacks, generalized defense, and interpretable backdoor analysis, this study aligns well with the themes of Trustworthy and Safe AI: Interpretability, Robustness, and Security.&lt;/p&gt;&lt;p&gt;In [&lt;span&gt;2&lt;/span&gt;], the authors study how a single malicious agent can compromise the collective decision-making of otherwise well-aligned LLM agents in a collaborative financial multi-agent environment and proposes a data-lineage-based systemic defense. Its main contribution is to show that the interaction dynamics themselves can become a security vulnerability, extending AI safety concerns beyond isolated models to multi-agent societies. By analyzing poisoning, social conformity, and system-level verification across multiple models and network settings, this study offers timely insights into the robustness, safety, and trustworthy coordination of emerging autonomous multi-agent AI systems.&lt;/p&gt;&lt;p&gt;The paper [&lt;span&gt;3&lt;/span&gt;] titled “Lost in the comments: Social context as a single-pass jailbreak and defense on agentic platforms” by Jeongsu Park and colleagues investigates how comments","PeriodicalId":11901,"journal":{"name":"ETRI Journal","volume":"48 5","pages":"763-767"},"PeriodicalIF":2.0,"publicationDate":"2026-10-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.4218/etr2.70162","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149222801","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"STPA-based analysis of driver misuse risk scenarios in level 3 automated driving","authors":"Yangkoo Lee,&nbsp;Eun Hye Jang,&nbsp;Mi Chang,&nbsp;Kezia Amanda Kurniadi,&nbsp;Jiwoo Han,&nbsp;Woojin Kim,&nbsp;Daesub Yoon","doi":"10.4218/etrij.2026-0204","DOIUrl":"https://doi.org/10.4218/etrij.2026-0204","url":null,"abstract":"<p>This paper proposes an analytical framework that integrates the SOTIF perspective with System-Theoretic Process Analysis (STPA) to systematically analyze driver misuse in Level 3 automated driving environments. In Lv.3 systems, drivers must intervene when Takeover Requests (TOR) occur, making misuse a critical safety risk even when the system operates as intended. Driver misuse is modeled as inadequate control actions within the control structure, and the four psychological states that induce misuse—overtrust, distrust, distraction, and interference—are treated as the causal factors of those unsafe control actions. Following the STPA procedure, 41 causal scenarios were derived and evaluated using severity, likelihood, and controllability. Clustering analysis was then applied to identify recurring risk patterns and representative Risk Archetypes. The results show that many high-risk scenarios are strongly related to drivers' failures to perceive or properly respond to TOR. The proposed framework provides a structured basis for understanding driver misuse risks and supports the design of driver monitoring, improved HMI strategies, and multilayer safety assistance mechanisms.</p>","PeriodicalId":11901,"journal":{"name":"ETRI Journal","volume":"48 5","pages":"868-883"},"PeriodicalIF":2.0,"publicationDate":"2026-10-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.4218/etrij.2026-0204","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149222842","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"LLM-guided semantic-aware trajectory optimization for UAV path planning using environmental context","authors":"Hanseob Lee,&nbsp;Hoon Jung","doi":"10.4218/etrij.2026-0245","DOIUrl":"https://doi.org/10.4218/etrij.2026-0245","url":null,"abstract":"<p>Autonomous unmanned aerial vehicle path planning in urban environments requires both geometric safety and semantic awareness. Conventional planners based on fixed costs or predefined risk models struggle to reflect mission-dependent semantic priorities. We present a large language model (LLM)-guided semantic-aware planning framework in which the LLM serves as a bounded high-level decision module. OpenStreetMap data are transformed into class-wise semantic potential fields, and a route-relative context and natural-language mission description are used to infer validated semantic modulation coefficients. A deterministic B-spline optimizer generates smooth paths by jointly considering multiple factors. Comparisons with existing models demonstrate a competitive tradeoff between path efficiency and semantic safety. Mission-conditioned experiments reveal that different mission descriptions produce distinct semantic policies and path geometries under identical environmental conditions. Reliability analysis indicates that the deterministic downstream planner maintains stable safety-related performance under context perturbations and stochastic LLM outputs.</p>","PeriodicalId":11901,"journal":{"name":"ETRI Journal","volume":"48 5","pages":"896-910"},"PeriodicalIF":2.0,"publicationDate":"2026-10-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.4218/etrij.2026-0245","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149222794","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Adaptive sampling-driven workload balancing for distributed data stream processing","authors":"Jiawei Tan,&nbsp;Li Yang,&nbsp;Wei Zhang,&nbsp;Xiong Xiao","doi":"10.4218/etrij.2025-0175","DOIUrl":"https://doi.org/10.4218/etrij.2025-0175","url":null,"abstract":"<p>Partitioning scheme in distributed stream processing systems is a critical factor in processing large-scale real-time data streams. Existing solutions either suffer from poor partition quality or high overhead in partitioning time, resulting in severe workload imbalance and backpressure problems. This paper proposes an adaptive sampling-driven workload balancing (ASWB) scheme to solve the above problem. ASWB introduces two core innovations: (1) an adaptive sampling rate algorithm driven by backpressure signals, which dynamically controls the stream sampling rate to avoid prediction bottlenecks and alleviate workload imbalance, and (2) a high-frequency key prediction module that leverages a variable-size window to reduce hash collisions and improve frequency estimation accuracy. This design accelerates the identification of high-frequency keys within the partition operator, thereby enhancing partitioning quality. We implement ASWB on Apache Flink and evaluate it using large-scale real-world datasets. Experimental results show that ASWB improves system throughput by up to 55.03% and reduces processing latency compared with state-of-the-art approaches.</p>","PeriodicalId":11901,"journal":{"name":"ETRI Journal","volume":"48 4","pages":"677-692"},"PeriodicalIF":2.0,"publicationDate":"2026-08-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.4218/etrij.2025-0175","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148784814","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Mix-MaxETTS: A text-to-emotional speech synthesis model based on a deep encoder–decoder structure for the transfer of secondary emotions","authors":"Seyyed Mahdi Hassani,&nbsp;Mohammad Reza Kangavari","doi":"10.4218/etrij.2025-0058","DOIUrl":"https://doi.org/10.4218/etrij.2025-0058","url":null,"abstract":"<p>Given the importance of emotions in social interactions, emotional speech synthesis has attracted significant attention in the field of human–computer interaction. Remarkable advancements have been made in emotional text-to-speech synthesis, but most previous studies have concentrated on imitating styles associated with a specific primary emotion, neglecting secondary emotions that arise from mixtures of primary emotions. Therefore, there is a need to leverage both primary and secondary emotions in speech synthesis to facilitate more engaging, realistic, and natural interactions among artificial social agents. To address this gap, we propose a text-to-emotional speech synthesis model designed to generate nuanced mixtures of emotions that effectively convey secondary emotions during interactions. By adjusting the values of each basic emotion, we can control the mix of emotions in the synthetic speech. Our proposed method distinguishes between primary emotions and variations in mixed emotions while learning emotional styles. The effectiveness of the proposed framework was validated through both objective and subjective evaluations.</p>","PeriodicalId":11901,"journal":{"name":"ETRI Journal","volume":"48 4","pages":"693-710"},"PeriodicalIF":2.0,"publicationDate":"2026-08-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.4218/etrij.2025-0058","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148785105","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Ka-Band GaN low-noise amplifier monolithic microwave integrated circuit using external source interconnect for gate-side parasitic suppression","authors":"Woojin Chang,&nbsp;Jong Yul Park,&nbsp;Kyu Jun Cho,&nbsp;Junhyung Jeong,&nbsp;Hong-Gu Ji,&nbsp;Byoung-Gue Min,&nbsp;Jong-Min Lee,&nbsp;Junhyung Kim,&nbsp;Gyejung Lee,&nbsp;Dong Min Kang","doi":"10.4218/etrij.2025-0282","DOIUrl":"https://doi.org/10.4218/etrij.2025-0282","url":null,"abstract":"<p>This paper presents a Ka-band low-noise amplifier (LNA) monolithic microwave integrated circuit (MMIC) using a GaN high-electron-mobility transistor (HEMT) structure designed to minimize gate–source parasitic capacitance (<i>C</i>_gs). In conventional multigate GaN HEMTs, internal source interconnects tie split sources, increasing parasitic coupling near the gate and degrading the minimum noise figure (NF_min) at millimeter-wave frequencies. To overcome this limitation, an external source interconnect is routed outside the active region, effectively suppressing gate-side parasitics and reducing <i>C</i>_gs, without compromising circuit integrity or layout compactness. The proposed five-stage common-source LNA MMIC, fabricated using ETRI's 0.15 μm GaN-on-SiC process, achieves a gain of 23–28 dB and a noise figure of 2.1–2.3 dB across 26–30 GHz. Compared with recently reported Ka-band GaN LNA MMICs, the design attains figures of merit: FoM₁ = 724 GHz/mm² and FoM₂ = 0.72 GHz/mW·mm². These improvements result from the reduced <i>C</i>_gs enabled by the external source interconnect and compact layout, confirming the suitability of the proposed HEMT structure for high-performance millimeter-wave front-end receivers requiring low-noise and efficient integration.</p>","PeriodicalId":11901,"journal":{"name":"ETRI Journal","volume":"48 4","pages":"731-746"},"PeriodicalIF":2.0,"publicationDate":"2026-08-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.4218/etrij.2025-0282","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148783690","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Artificial magnetic conductor-integrated high-gain quad-port hexagonal antenna for conformal ultra-wideband applications","authors":"Bandi Alekya,&nbsp;Neelaveni Ammal Murugan,&nbsp;Boddapati Taraka Phani Madhav","doi":"10.4218/etrij.2025-0252","DOIUrl":"https://doi.org/10.4218/etrij.2025-0252","url":null,"abstract":"<p>This article presents a hexagonal multiple-input–multiple-output (MIMO) antenna with dimensions of 60 × 60 × 0.1 mm³ on a flexible substrate operating within the 2–12 GHz frequency range. The design includes a specially engineered defective ground structure that improves inter-element isolation to &gt;25 dB. The proposed design achieves an impedance bandwidth of 142.85% (|\u0000<span></span><math>\u0000 <msub>\u0000 <mi>S</mi>\u0000 <mn>11</mn>\u0000 </msub></math>| &lt; −10 dB). A circular split-ring-shaped artificial magnetic conductor (AMC) of size 80 × 80 × 0.1 mm³ is placed beneath the engineered radiator to enhance gain by up to 9.6 dBi and reduce the specific absorption rate (SAR). Both the antenna and AMC structure are printed on a 0.1-mm-thin polyamide substrate. The performance of key diversity metrics of the proposed MIMO antenna is evaluated, and the results confirm its efficacy. On-body performance analysis reveals that the SAR remains &lt;0.06 W/kg when the radiator is placed on the forearm and &lt;0.16 W/kg when placed on the leg and head. A prototype is fabricated and evaluated through testing, confirming that the proposed structure is highly suited for wireless body area network and 5G communication applications.</p>","PeriodicalId":11901,"journal":{"name":"ETRI Journal","volume":"48 4","pages":"604-619"},"PeriodicalIF":2.0,"publicationDate":"2026-08-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.4218/etrij.2025-0252","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148783684","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Performance comparison of object detection models for video analytics under varying video compression quality conditions","authors":"Kholidiyah Masykuroh,&nbsp; Hendrawan,&nbsp;Eueung Mulyana","doi":"10.4218/etrij.2025-0363","DOIUrl":"https://doi.org/10.4218/etrij.2025-0363","url":null,"abstract":"<p>Video analytics (VA) systems are becoming increasingly reliant on deep-neural-network-based object detection, where video compression parameters such as resolution, bitrate, and quantization significantly affect inference accuracy. This paper presents a benchmarking study on five object detection models, namely Fast R-CNN, EfficientDet, YOLOv5, YOLOv8, and DETR, which were evaluated using three encoder-defined video quality levels (High, Medium, and Low). Performance was assessed using bitrate (Mbps), peak signal-to-noise ratio (PSNR, dB), and detection accuracy to provide a reproducible framework for analyzing compression-induced performance variations. Experimental results reveal that PSNR scales approximately linearly with bitrate, whereas detection accuracy exhibits saturation with diminishing returns at higher bitrates. YOLOv5 exhibited the highest robustness to compression, followed by Fast R-CNN and DETR, whereas EfficientDet and YOLOv8 were more sensitive to quality degradation. We identify practical operating points that balance accuracy and bandwidth efficiency, providing actionable guidance for model–codec co-design in surveillance and smart-city VA applications.</p>","PeriodicalId":11901,"journal":{"name":"ETRI Journal","volume":"48 4","pages":"620-634"},"PeriodicalIF":2.0,"publicationDate":"2026-08-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.4218/etrij.2025-0363","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148783735","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Optimized artificial neural network for vocal gender expression classification","authors":"Mohamed Mansoor Roomi Sindha,&nbsp;Priya Kannapiran,&nbsp;Uma Maheswari Pandyan,&nbsp;Mathu Sudhanan Sreenivasan","doi":"10.4218/etrij.2024-0608","DOIUrl":"https://doi.org/10.4218/etrij.2024-0608","url":null,"abstract":"<p>Gender expression is a complex and multidimensional characteristic that goes beyond traditional binary models, especially regarding vocal attributes. Existing voice gender recognition systems often rely on binary classification, which fails to capture the subtle spectrum of gender expressions in natural speech. To address this limitation, we introduce the FEMASC dataset, which is a novel resource that categorizes voice signals into five classes (absolute male, strong male, ambiguous, strong female, and absolute female) reflecting varying degrees of masculinity and femininity. In addition, we propose an optimized artificial neural network that uses feature fusion and Bayesian hyperparameter tuning to effectively model subtle variations in vocal features. Our approach not only overcomes the constraints of binary classification but also achieves robust performance with a precision of 86.8%, recall of 86.1%, <i>F</i>₁ score of 86.2%, and accuracy of 82% on the FEMASC dataset. These results demonstrate that a multiclass framework supported by a carefully designed dataset and advanced modeling techniques offers significant improvement in voice gender expression recognition.</p>","PeriodicalId":11901,"journal":{"name":"ETRI Journal","volume":"48 4","pages":"663-676"},"PeriodicalIF":2.0,"publicationDate":"2026-08-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.4218/etrij.2024-0608","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148785061","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}