In this study, we evaluate potential demographic bias in state-of-the-art deepfake image detection models across three key attributes: age, ethnicity, and gender. Unlike prior works that retrain detectors or analyse forensic manipulations, we systematically assess multiple pretrained checkpoints of leading deepfake detectors, each trained on different datasets, to ensure an unbiased evaluation framework. Our experiments employ synthetic images generated by recent diffusion and autoregressive models, alongside real images from balanced datasets, to measure subgroup-specific detection performance. Results reveal no systematic bias across demographic categories—variations in accuracy and precision remain within small statistical margins across all detectors and checkpoints. We further provide a taxonomy of image generative models, highlighting their evolution from pixel-space to latent-space diffusion architectures, to contextualize the diversity of synthetic data used in our evaluation. Overall, our findings suggest that modern deepfake image detectors, when tested in a cross-demographic setting using pretrained checkpoints, exhibit robust and fair performance across age, ethnicity, and gender.
{"title":"Bias-Free? An Empirical Study on Ethnicity, Gender, and Age Fairness in Deepfake Detection","authors":"Aditi Panda, Tanusree Ghosh, Tushar Choudhary, Ruchira Naskar","doi":"10.1145/3796544","DOIUrl":"https://doi.org/10.1145/3796544","url":null,"abstract":"In this study, we evaluate potential demographic bias in state-of-the-art deepfake image detection models across three key attributes: age, ethnicity, and gender. Unlike prior works that retrain detectors or analyse forensic manipulations, we systematically assess multiple pretrained checkpoints of leading deepfake detectors, each trained on different datasets, to ensure an unbiased evaluation framework. Our experiments employ synthetic images generated by recent diffusion and autoregressive models, alongside real images from balanced datasets, to measure subgroup-specific detection performance. Results reveal no systematic bias across demographic categories—variations in accuracy and precision remain within small statistical margins across all detectors and checkpoints. We further provide a taxonomy of image generative models, highlighting their evolution from pixel-space to latent-space diffusion architectures, to contextualize the diversity of synthetic data used in our evaluation. Overall, our findings suggest that modern deepfake image detectors, when tested in a cross-demographic setting using pretrained checkpoints, exhibit robust and fair performance across age, ethnicity, and gender.","PeriodicalId":50926,"journal":{"name":"ACM Computing Surveys","volume":"40 4 1","pages":""},"PeriodicalIF":16.6,"publicationDate":"2026-02-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146153682","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-02-09DOI: 10.1109/jiot.2026.3662407
Runkai Song, Fan Qin, Wenchi Cheng, Steven Gao
{"title":"Flexible Wearable Filtering Antenna With Stable Performance for IoT Devices","authors":"Runkai Song, Fan Qin, Wenchi Cheng, Steven Gao","doi":"10.1109/jiot.2026.3662407","DOIUrl":"https://doi.org/10.1109/jiot.2026.3662407","url":null,"abstract":"","PeriodicalId":54347,"journal":{"name":"IEEE Internet of Things Journal","volume":"60 1","pages":""},"PeriodicalIF":10.6,"publicationDate":"2026-02-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146145973","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-02-09DOI: 10.1109/tac.2026.3662563
Alexandre Didier, Melanie N. Zeilinger
{"title":"Approximate Predictive Control Barrier Function for Discrete-Time Systems","authors":"Alexandre Didier, Melanie N. Zeilinger","doi":"10.1109/tac.2026.3662563","DOIUrl":"https://doi.org/10.1109/tac.2026.3662563","url":null,"abstract":"","PeriodicalId":13201,"journal":{"name":"IEEE Transactions on Automatic Control","volume":"133 1","pages":""},"PeriodicalIF":6.8,"publicationDate":"2026-02-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146146129","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-02-09DOI: 10.1016/j.jnca.2026.104438
Zainab Alwaisi, Tanesh Kumar, Simone Soderi
Next-generation IoT wireless communication systems emphasise the importance and urgent need for energy-efficient security measures, thus requiring a balanced approach to address growing security vulnerabilities and fulfil energy demands in advanced wireless communication networks. However, the evolution of 6G networks and their integration with advanced technologies will revolutionise the IoT ecosystem while simultaneously introducing new security threats such as the Mirai malware, which targets IoT devices, infects multiple nodes, and depletes computational and energy resources. This study introduces a novel security algorithm designed to minimise energy consumption while effectively detecting botnet attacks at the smart device level. This research examines four distinct types of Mirai botnet attacks: scan, UDP, TCP, and ACK flooding.The experimental evaluation was conducted using real IoT device data collected from a Raspberry Pi setup combined with network traffic traces simulating the four Mirai attack scenarios to ensure realistic and reproducible results. Two ML algorithms, SVM and KNN, are employed to detect these botnet attacks, with each algorithm’s detection accuracy and energy efficiency thoroughly assessed. Results indicate that the proposed approach significantly enhances smart device security while minimising energy use. Findings show that the KNN algorithm outperforms SVM in terms of accuracy and energy efficiency for detecting Mirai botnet attacks, achieving detection rates above 99% across various attack types. This study highlights the importance of selecting suitable security techniques for IoT networks to address the evolving threats and energy demands of 6G-enabled wireless communication systems, providing valuable insights for future research.
{"title":"Robust and energy-aware detection of Mirai botnet for future 6G-enabled IoT networks","authors":"Zainab Alwaisi, Tanesh Kumar, Simone Soderi","doi":"10.1016/j.jnca.2026.104438","DOIUrl":"https://doi.org/10.1016/j.jnca.2026.104438","url":null,"abstract":"Next-generation IoT wireless communication systems emphasise the importance and urgent need for energy-efficient security measures, thus requiring a balanced approach to address growing security vulnerabilities and fulfil energy demands in advanced wireless communication networks. However, the evolution of 6G networks and their integration with advanced technologies will revolutionise the IoT ecosystem while simultaneously introducing new security threats such as the Mirai malware, which targets IoT devices, infects multiple nodes, and depletes computational and energy resources. This study introduces a novel security algorithm designed to minimise energy consumption while effectively detecting botnet attacks at the smart device level. This research examines four distinct types of Mirai botnet attacks: scan, UDP, TCP, and ACK flooding.The experimental evaluation was conducted using real IoT device data collected from a Raspberry Pi setup combined with network traffic traces simulating the four Mirai attack scenarios to ensure realistic and reproducible results. Two ML algorithms, SVM and KNN, are employed to detect these botnet attacks, with each algorithm’s detection accuracy and energy efficiency thoroughly assessed. Results indicate that the proposed approach significantly enhances smart device security while minimising energy use. Findings show that the KNN algorithm outperforms SVM in terms of accuracy and energy efficiency for detecting Mirai botnet attacks, achieving detection rates above 99% across various attack types. This study highlights the importance of selecting suitable security techniques for IoT networks to address the evolving threats and energy demands of 6G-enabled wireless communication systems, providing valuable insights for future research.","PeriodicalId":54784,"journal":{"name":"Journal of Network and Computer Applications","volume":"1 1","pages":""},"PeriodicalIF":8.7,"publicationDate":"2026-02-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146146704","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-02-09DOI: 10.1109/tnnls.2026.3657138
Basit Alawode, Iyyakutti Iyappan Ganapathi, Sajid Javed, Mohammed Bennamoun, Arif Mahmood
{"title":"AquaticCLIP: A Vision-Language Foundation Model and Dataset for Underwater Scene Analysis","authors":"Basit Alawode, Iyyakutti Iyappan Ganapathi, Sajid Javed, Mohammed Bennamoun, Arif Mahmood","doi":"10.1109/tnnls.2026.3657138","DOIUrl":"https://doi.org/10.1109/tnnls.2026.3657138","url":null,"abstract":"","PeriodicalId":13303,"journal":{"name":"IEEE transactions on neural networks and learning systems","volume":"161 1","pages":""},"PeriodicalIF":10.4,"publicationDate":"2026-02-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146146044","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-02-09DOI: 10.1109/jiot.2026.3662758
Haowen Zhang, Juan Li, Qing Yao
{"title":"RACER: Fast and Accurate Time Series Clustering with Random Convolutional Kernels and Ensemble Methods","authors":"Haowen Zhang, Juan Li, Qing Yao","doi":"10.1109/jiot.2026.3662758","DOIUrl":"https://doi.org/10.1109/jiot.2026.3662758","url":null,"abstract":"","PeriodicalId":54347,"journal":{"name":"IEEE Internet of Things Journal","volume":"314 1","pages":""},"PeriodicalIF":10.6,"publicationDate":"2026-02-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146146092","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：