Jaime C. Acosta
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Jaime C. Acosta has a total of 34 co-authors. Here are the top co-authors by number of shared publications:
- Charles Kamhoua
DEVCOM Army Research Laboratory
4 shared publications - Danda B. Rawat
Howard University
3 shared publications - Elie Tagne Fute
Department of Computer Engineering, Faculty of Engineering and Technology (FET), University of Buea, Buea, Cameroon
3 shared publications - Elisabeth Tchaptchet
Mathematics and Computer Science Department, University of Dschang, Dschang, Cameroon
3 shared publications - Christopher Kiekintveld
University of Texas at El Paso
2 shared publications - Ahmed Hemida Anwar
DEVCOM Army Research Laboratory, Adelphi, MD, USA
1 shared publication
Latest Publications
- 15 January 2026
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 85 (1) , 3
Deepfake detection using a distinctive eye signature and the entropy heat map of the image texture
- 15 January 2026
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 85 (1) , 3
Deepfake detection using a distinctive eye signature and the entropy heat map of the image texture
- 16 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Security & Privacy
- Vol. 23 (6) , 58-65
Learning-Based Internet of Things Honeypots for Cyber Deception
HoneyIoT is a high-interaction Internet of Things honeypot that leverages reinforcement learning to adaptively engage and deceive attackers. We demonstrate its superior performance over existing approaches, identify recent trends in attacker evolution, and point out directions for future research.
- 16 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Security & Privacy
- Vol. 23 (6) , 58-65
Learning-Based Internet of Things Honeypots for Cyber Deception
HoneyIoT is a high-interaction Internet of Things honeypot that leverages reinforcement learning to adaptively engage and deceive attackers. We demonstrate its superior performance over existing approaches, identify recent trends in attacker evolution, and point out directions for future research.
- Open Access
- 30 April 2025
- Published by MDPI AG in Information
- Vol. 16 (5) , 371
The Eyes: A Source of Information for Detecting Deepfakes
Currently, the phenomenon of deepfakes is becoming increasingly significant, as they enable the creation of extremely realistic images capable of deceiving anyone thanks to deep learning tools based on generative adversarial networks (GANs). These images are used as profile pictures on social media with the intent to sow discord and perpetrate scams on a global scale. In this study, we demonstrate that these images can be identified through various imperfections present in the synthesized eyes, such as the irregular shape of the pupil and the difference between the corneal reflections of the two eyes. These defects result from the absence of physical and physiological constraints in most GAN models. We develop a two-level architecture capable of detecting these fake images. This approach begins with an automatic segmentation method for the pupils to verify their shape, as real image pupils naturally have a regular shape, typically round. Next, for all images where the pupils are not regular, the entire image is analyzed to verify the reflections. This step involves passing the facial image through an architecture that extracts and compares the specular reflections of the corneas of the two eyes, assuming that the eyes of real people observing a light source should reflect the same thing. Our experiments with a large dataset of real images from the Flickr-FacesHQ and CelebA datasets, as well as fake images from StyleGAN2 and ProGAN, show the effectiveness of our method. Our experimental results on the Flickr-Faces-HQ (FFHQ) dataset and images generated by StyleGAN2 demonstrated that our algorithm achieved a remarkable detection accuracy of 0.968 and a sensitivity of 0.911. Additionally, the method had a specificity of 0.907 and a precision of 0.90 for this same dataset. And our experimental results on the CelebA dataset and images generated by ProGAN also demonstrated that our algorithm achieved a detection accuracy of 0.870 and a sensitivity of 0.901. Moreover, the method had a specificity of 0.807 and a precision of 0.88 for this same dataset. Our approach maintains good stability of physiological properties during deep learning, making it as robust as some single-class deepfake detection methods. The results of the tests on the selected datasets demonstrate higher accuracy compared to other methods.
- 30 April 2025
- Published by MDPI AG in Information
- Vol. 16 (5) , 371
Open AccessThe Eyes: A Source of Information for Detecting Deepfakes
Currently, the phenomenon of deepfakes is becoming increasingly significant, as they enable the creation of extremely realistic images capable of deceiving anyone thanks to deep learning tools based on generative adversarial networks (GANs). These images are used as profile pictures on social media with the intent to sow discord and perpetrate scams on a global scale. In this study, we demonstrate that these images can be identified through various imperfections present in the synthesized eyes, such as the irregular shape of the pupil and the difference between the corneal reflections of the two eyes. These defects result from the absence of physical and physiological constraints in most GAN models. We develop a two-level architecture capable of detecting these fake images. This approach begins with an automatic segmentation method for the pupils to verify their shape, as real image pupils naturally have a regular shape, typically round. Next, for all images where the pupils are not regular, the entire image is analyzed to verify the reflections. This step involves passing the facial image through an architecture that extracts and compares the specular reflections of the corneas of the two eyes, assuming that the eyes of real people observing a light source should reflect the same thing. Our experiments with a large dataset of real images from the Flickr-FacesHQ and CelebA datasets, as well as fake images from StyleGAN2 and ProGAN, show the effectiveness of our method. Our experimental results on the Flickr-Faces-HQ (FFHQ) dataset and images generated by StyleGAN2 demonstrated that our algorithm achieved a remarkable detection accuracy of 0.968 and a sensitivity of 0.911. Additionally, the method had a specificity of 0.907 and a precision of 0.90 for this same dataset. And our experimental results on the CelebA dataset and images generated by ProGAN also demonstrated that our algorithm achieved a detection accuracy of 0.870 and a sensitivity of 0.901. Moreover, the method had a specificity of 0.807 and a precision of 0.88 for this same dataset. Our approach maintains good stability of physiological properties during deep learning, making it as robust as some single-class deepfake detection methods. The results of the tests on the selected datasets demonstrate higher accuracy compared to other methods.
- Open Access
- 27 December 2024
- Published by MDPI AG in Preprints.org
The Eyes: A Source of Information for Detecting Deepfakes
Nowadays, the phenomenon of Deepfake is crucial as it enables the creation of extremely realistic images capable of deceiving anyone, thanks to deep learning tools based on Generative Adversarial Networks (GANs). These images are used as profile pictures on social media with the intent to sow discord and perpetrate scams on a global scale. In this study, we demonstrate that these images can be identified through various imperfections present in the synthesized eyes, such as the irregular shape of the pupil and the difference between the corneal reflections of the two eyes. These defects result from the absence of physical and physiological constraints in most GAN models. We have developed a two-level architecture capable of detecting these fake images. This approach begins with an automatic segmentation method for the pupils to verify their shape, as real image pupils naturally have a regular shape, typically round. Next, for all images where the pupils are not regular, the entire image is analyzed to verify the reflections. This step involves passing the facial image through an architecture that extracts and compares the specular reflections of the corneas of the two eyes, assuming that the eyes of real people observing a light source should reflect the same thing. Our experiments with a large dataset of real images from the Flickr-FacesHQ and CelebA datasets, as well as fake images from StyleGAN2 and ProGAN, show the effectiveness of our method. Our approach maintains good stability of physiological properties during deep learning, making it as robust as some single-class deepfake detection methods. The results of the tests on the selected datasets demonstrate higher accuracy compared to other methods.
- 27 December 2024
- Published by MDPI AG in Preprints.org
Open AccessThe Eyes: A Source of Information for Detecting Deepfakes
Nowadays, the phenomenon of Deepfake is crucial as it enables the creation of extremely realistic images capable of deceiving anyone, thanks to deep learning tools based on Generative Adversarial Networks (GANs). These images are used as profile pictures on social media with the intent to sow discord and perpetrate scams on a global scale. In this study, we demonstrate that these images can be identified through various imperfections present in the synthesized eyes, such as the irregular shape of the pupil and the difference between the corneal reflections of the two eyes. These defects result from the absence of physical and physiological constraints in most GAN models. We have developed a two-level architecture capable of detecting these fake images. This approach begins with an automatic segmentation method for the pupils to verify their shape, as real image pupils naturally have a regular shape, typically round. Next, for all images where the pupils are not regular, the entire image is analyzed to verify the reflections. This step involves passing the facial image through an architecture that extracts and compares the specular reflections of the corneas of the two eyes, assuming that the eyes of real people observing a light source should reflect the same thing. Our experiments with a large dataset of real images from the Flickr-FacesHQ and CelebA datasets, as well as fake images from StyleGAN2 and ProGAN, show the effectiveness of our method. Our approach maintains good stability of physiological properties during deep learning, making it as robust as some single-class deepfake detection methods. The results of the tests on the selected datasets demonstrate higher accuracy compared to other methods.
- Open Access
- 1 October 2024
- Published by MDPI AG in Journal of Cybersecurity and Privacy
- Vol. 4 (4) , 794-804
Detection of Hacker Intention Using Deep Packet Inspection
Ideally, in a real cyberattack, the early detection of probable hacker intent can lead to improved mitigation or prevention of exploitation. With the knowledge of basic principles of communication protocols, the reconnaissance/scanning phase intentions of a hacker can be inferred by detecting specific patterns of behavior associated with hacker tools and commands. Analyzing the reconnaissance behavior of the TCP Syn Scan between Nmap and the host, we built machine learning models incorporating the use of a filtering method we developed for labeling a dataset for detection of this behavior. We conclude that feature selection and detailed targeted labeling, based on behavior patterns, yield a high accuracy and F1 Score using Random Forest and Logistics Regression classifiers.
- 1 October 2024
- Published by MDPI AG in Journal of Cybersecurity and Privacy
- Vol. 4 (4) , 794-804
Open AccessDetection of Hacker Intention Using Deep Packet Inspection
Ideally, in a real cyberattack, the early detection of probable hacker intent can lead to improved mitigation or prevention of exploitation. With the knowledge of basic principles of communication protocols, the reconnaissance/scanning phase intentions of a hacker can be inferred by detecting specific patterns of behavior associated with hacker tools and commands. Analyzing the reconnaissance behavior of the TCP Syn Scan between Nmap and the host, we built machine learning models incorporating the use of a filtering method we developed for labeling a dataset for detection of this behavior. We conclude that feature selection and detailed targeted labeling, based on behavior patterns, yield a high accuracy and F1 Score using Random Forest and Logistics Regression classifiers.
- 27 February 2024
- Published by Defense Technical Information Center (DTIC)
Themis Deep Packet Inspection (DPI) Evasion Detection
Open-source network intrusion detection systems (NIDS) such as Snort, Suricata, and Zeek rely primarily on signature- and anomaly-based detection techniques. These systems also deploy deep packet inspection (DPI) to analyze the data as it would be used by its final application layer. Malicious actors often use evasion techniques to avoid these NIDS. This study analyzed several DPI methods versus Themis DPI and Zeek detection capabilities.
- 27 February 2024
- Published by Defense Technical Information Center (DTIC)
Themis Deep Packet Inspection (DPI) Evasion Detection
Open-source network intrusion detection systems (NIDS) such as Snort, Suricata, and Zeek rely primarily on signature- and anomaly-based detection techniques. These systems also deploy deep packet inspection (DPI) to analyze the data as it would be used by its final application layer. Malicious actors often use evasion techniques to avoid these NIDS. This study analyzed several DPI methods versus Themis DPI and Zeek detection capabilities.
- 11 December 2023
- Published by Defense Technical Information Center (DTIC)
Hands-On Cybersecurity Studies: Ghidra Plugin Scripts for Simple Decoding
This document describes a hands-on cybersecurity exercise that focuses on developing a plugin script for the Ghidra publicly available and open-source software tool released by the National Security Agency in 2019. In the exercise, participants learn the basics of the tool and are then tasked with creating scripts that will automatically decode portions of a file to identify pertinent information.
- 11 December 2023
- Published by Defense Technical Information Center (DTIC)
Hands-On Cybersecurity Studies: Ghidra Plugin Scripts for Simple Decoding
This document describes a hands-on cybersecurity exercise that focuses on developing a plugin script for the Ghidra publicly available and open-source software tool released by the National Security Agency in 2019. In the exercise, participants learn the basics of the tool and are then tasked with creating scripts that will automatically decode portions of a file to identify pertinent information.
- 7 December 2023
- Published by Defense Technical Information Center (DTIC)
Hands-On Cybersecurity Studies: Automated Scan Tool Detection
This special report describes a hands-on cybersecurity exercise that focuses on novel research aimed at automatically collecting data and generating intrusion detection system (IDS) rules using the Generate, Examine, Match (GEM) system. In the exercise, participants create a network scenario and learn how to collect and analyze the traffic generated by a network scanning tool. Afterward, they create an IDS rule by hand. The subsequent steps lead students through how to use the GEM tool and then they automatically create IDS rules.
- 7 December 2023
- Published by Defense Technical Information Center (DTIC)
Hands-On Cybersecurity Studies: Automated Scan Tool Detection
This special report describes a hands-on cybersecurity exercise that focuses on novel research aimed at automatically collecting data and generating intrusion detection system (IDS) rules using the Generate, Examine, Match (GEM) system. In the exercise, participants create a network scenario and learn how to collect and analyze the traffic generated by a network scanning tool. Afterward, they create an IDS rule by hand. The subsequent steps lead students through how to use the GEM tool and then they automatically create IDS rules.
- 1 November 2023
- Published by Springer Nature
- p. 536-549
Automatic Data Generation and Rule Creation for Network Scanning Tools
- 1 November 2023
- Published by Springer Nature
- p. 536-549
Automatic Data Generation and Rule Creation for Network Scanning Tools