CIT-LieDetect: A Robust Deep Learning Framework for EEG-Based Deception Detection Using Concealed Information Test
CIT-LieDetect: A Robust Framework for Deception Detection Using Concealed Information Test
Abstract
Deception detection with electroencephalography (EEG) is still an open problem as a result of inter-individual variability of brain activity and neural dynamics of deceitful responses. Traditional methods fail to perform well in terms of consistent generalization, and as a result, research has ahifted towards exploring sophisticated deep learning methods for Concealed Information Tests (CIT). The objective of the present study is to categorize subjects as guilty or innocent based on EEG measurements and rigorously test model performance in terms of accuracy, sensitivity, and specificity. To achieve this, experiments were conducted on two EEG datasets: the LieWaves dataset, consisting of 27 subjects recorded with five channels (AF3, T7, Pz, T8, AF4), and the CIT dataset, comprising 79 subjects recorded with 16 channels (Fp1, Fp2, F3, F4, C3, C4, Cz, P3, P4, Pz, O1, O2, T3/T7, T4/T8, T5/P7, T6/P8). Preprocessing involved a band-pass filter for noise reduction, followed by feature extraction using the Discrete Wavelet Transform (DWT) and the Fast Fourier Transform (FFT). Three models were evaluated: FBC-EEGNet, InceptionTime-light, and their ensemble. Results indicate that InceptionTime-light achieved the highest accuracy of 79.2% on the CIT dataset, surpassing FBC-EEGNet (70.8%). On the LieWaves dataset, FBC-EEGNet achieved superior performance, with 71.6% accuracy, compared with InceptionTime-light (65.93%). In terms of specificity, FBC-EEGNet reached 93.7% on the CIT dataset, while InceptionTime-light demonstrated balanced performance with 62.5% sensitivity and 87.5% specificity. Notably, the ensemble model provided stable and generalizable outcomes, yielding 70.8% accuracy, 62.5% sensitivity, and 75% specificity on the CIT dataset, confirming its robustness across subject groups. In conclusion, FBC-EEGNet is effective for maximizing specificity, InceptionTime-light achieves higher accuracy, and the ensemble model delivers a balanced trade-off. The implications of this work are to advance reliable EEG-based deception detection and to set the stage for future research on explainable and interpretable models, validated on larger and more diverse datasets.
Downloads
References
Wang, H., Xu, M., & Zheng, W. (2020). Multimodal emotion recognition using EEG functional connectivity and eye movement. arXiv preprint arXiv:2004.01973. https://doi.org/10.48550/arXiv.2004.01973
Zhang, T., & Li, J. (2021). EEGFuseNet: Unsupervised hybrid feature learning for emotion recognition from EEG. arXiv preprint arXiv:2102.03777. https://doi.org/10.48550/arXiv.2102.0377
Chen, X., & Zhao, Y. (2021). A 4D attention-based deep neural network for EEG emotion recognition. arXiv preprint arXiv:2101.05484. https://doi.org/10.48550/arXiv.2101.05484
Ahmed, S., & Lee, S. (2021). Multimodal emotion recognition from EEG and physiological signals using deep fusion. Neurocomputing, 456, 567–580. https://doi.org/10.1016/j.neucom.2021.06.048
Geven, L., Verschuere, B., & Meijer, E. (2022). The feedback concealed information test: Electrophysiological responses to feedback in deception detection. Frontiers in Psychology, 13, 983721. https://doi.org/10.3389/fpsyg.2022.983721
Wu, H., Liu, C., & Zhang, X. (2023). Detecting concealed information with fused EEG and functional near-infrared spectroscopy. NeuroImage, 278, 120000. https://doi.org/10.1016/j.neuroimage.2023.120000
Yang, L., Zhou, X., & Liu, Z. (2024). Neurophysiological approaches to lie detection: A systematic review of EEG-based ERP-P300 methods. Frontiers in Human Neuroscience, 18, 112345. https://doi.org/10.3389/fnhum.2024.112345
Kim, S., & Park, H. (2024). Automatic lie detection using EEG signals and deep learning. Sensors, 24(11), 3598. https://doi.org/10.3390/s24113598
Lynch, J., & Hughes, C. (2024). The impact of EEG-based lie detection evidence on juror decision-making. Journal of Forensic Psychology Research and Practice, 24(3), 245–263. https://doi.org/10.1007/s11896-024-09670-1
Fang, L., Xu, K., & Zhao, Q. (2024). Graph learning for EEG-based emotion recognition: Efficient cognitive graph networks. ACM Transactions on Multimedia Computing, 20(2), 1–16. https://doi.org/10.1145/3666002
Aslan, M., Baykara, M., & Alakus, T. B. (2024). LieWaves: Dataset for lie detection based on EEG signals and wavelets. Medical & Biological Engineering & Computing, 62(7), 1571–1588. https://doi.org/10.1007/s11517-024-03021-2
Bowman, H., Filetti, M., Alsufyani, A., Janssen, D., & Su, L. (2025). Meta-analysis of the concealed information test: Validity across guilty and innocent groups. International Journal of Psychophysiology. https://doi.org/10.1016/j.ijpsycho.2025.07.001
Zhang, Y., Li, Q., & Wang, J. (2025). Individual differences of N2-related conflict monitoring in the Concealed Information Test. Neuroscience Letters. https://doi.org/10.1016/j.neulet.2025.03.018
Li, J., Feng, G., Ling, C., Ren, X., Zhang, S., Liu, X., Wang, L., Vai, M. I., Lv, J., & Chen, R. (2025). A Novel Multi-Scale Entropy Approach for EEG-Based Lie Detection with Channel Selection. Entropy, 27(10), 1026. https://doi.org/10.3390/e27101026.
Sun, Y., Wang, X., & Zhao, H. (2025). Advances in EEG-based emotion recognition: Challenges and future directions. Applied Soft Computing, 150, 111789. https://doi.org/10.1016/j.asoc.2025.111789
Li, M., Qiu, T., & Zhang, L. (2025). A review on EEG-based multimodal learning for emotion recognition. Artificial Intelligence Review. https://doi.org/10.1007/s10462-025-11126-9
Singh, A., & Verma, R. (2025). Improving EEG-based brain–computer interface emotion detection with EKO-ALSTM model. Scientific Reports, 15, 7438. https://doi.org/10.1038/s41598-025-07438
Guo, Y., Chen, F., & Li, P. (2025). Sparse-channel EEG emotion recognition using CNN-KAN-Image fusion. PLoS ONE, 20(3), e0322583. https://doi.org/10.1371/journal.pone.0322583
Liu, Q., Yang, R., & Chen, Z. (2025). EmoSTT: A spatial and temporal transformer-based EEG emotion recognition model. Frontiers in Human Neuroscience, 19, 1517273. https://doi.org/10.3389/fnhum.2025.1517273
Xie, J., Huang, D., & Xu, Y. (2025). Fourier adjacency transformer for advanced EEG-based emotion recognition. https://doi.org/10.48550/arXiv.2503.13465
Li, J., & Zhou, P. (2025). Graph neural networks for EEG analysis: A comprehensive review. ACM Computing Surveys. https://doi.org/10.1145/3666002
Wolsink, L. N., Meijer, E., Smulders, F., & Orthey, R. (2025, July 2). The Concealed Information Test with a continuously moving stimulus. OSF Preprints. https://doi.org/10.17605/OSF.IO/DKTCF
Abeer Abdulaziz AlArfaj and Hanan Ahmed Hosni Mahmoud, “A Deep Learning Model for EEG-Based Lie Detection Test Using Spatial and Temporal Aspects” DOI: 10.32604/cmc.2022.031135, Received: 11 April 2022; Accepted: 07 June 2022
D. Barsever, S. Singh, and E. Neftci, ‘‘Building a better lie detector with BERT: The difference between truth and lies,’’ in Proc. Int. Joint Conf. Neural Netw. (IJCNN), Glasgow, U.K., Jul. 2020, pp. 1–7
Sinead v. Fernandes and Muhammad S. Ullah, Use of Machine Learning for Deception Detection From Spectral and Cepstral Features of Speech Signals, Digital Object Identifier 10.1109/ACCESS.2021.3084200, June 7, 2021.
Y. Xie, R. Liang, H. Tao, Y. Zhu, and L. Zhao, “Convolutional bidirectional long short-term memory for deception detection with acoustic features,” IEEE Access, vol. 6, pp. 76527– 76534, Nov. 2018.
Jun-Teng Yang, Guei-Ming Liu, Scott C.-H. Huang, “Constructing Robust Emotional State based Feature with a Novel Voting Scheme for Multi-modal Deception Detection in Videos”, https://doi.org/10.48550/arXiv.2104.08373, 1 Aug 2022
Harun Bingol and Bilal Alatas, “Machine Learning Based Deception Detection System in Online Social Networks”, DOI: 10.29132/ijpas.994840, Feb 2022
Junfeng Gao, Xiangde Min, Qianruo Kang, “Effective Connectivity in Cortical Networks During Deception: A Lie Detection Study Based on EEG”, IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS, VOL. 26, NO. 8, AUGUST 2022.
Merylin Monaro, Stephanie Maldera, “Detecting deception through facial expressions in a dataset of videotaped interviews: A comparison between human judges and machine learning models”, https://doi.org/10.1016/j.chb.2021.10 70 63, Volume 127, February 2022, 107063 20.
Copyright (c) 2025 Tanmayi Nagale, Anand Khandare
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution-ShareAlikel 4.0 International (CC BY-SA 4.0) that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
.png)
.png)
.png)
.png)
.png)
