A deep learning approach for detecting covert timing channel attacks using sequential data

Al-Eidi, Shorouq; Darwish, Omar; Chen, Yuanzhu; Maabreh, Majdi; Tashtoush, Yahya

doi:10.1007/s10586-023-04035-5

Cited by 3 publications

(2 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In particular, new research in [21] Four deep learning models, including LSTM, 1D-CNN, and hybrid CNN-LSTM models for CTC, was proposed by Al-Eidi et al According to their result findings, the LSTM-CNN detection model achieved a high performance compared to other machine learning and deep learning models. However, successful deployment often necessitates working with large, diverse datasets and utilizing significant computational resources.…”

Section: Related Workmentioning

confidence: 99%

LinguTimeX: Explainable AI of Natural Language Detection in Leakage Information with Covert Timing Channels

Darwish,

Al-Eidi,

Al-Shorman

et al. 2024

Preprint

View full text Add to dashboard Cite

CCovert timing channels (CTC) enable surreptitious information leakage through manipulated data transmission timing, posing a severe cybersecurity risk. This research introduces a framework, called LinguTimeX, which utilizes explainable artificial intelligence approach that synergizes linguistic analysis with detection of timing irregularities to pinpoint CTC activities with high accuracy. The LinguTimeX extracts multidimensional features integrating statistical properties of textual content and temporal characteristics. An ensemble of machine learning and deep learning models, tailored for cross-lingual covert channel identification , demonstrates outstanding detection performance, with over 98% precision and recall in Arabic and 81% F1-score in Chinese datasets. Quantitative analysis and visualizations elucidate how innate language complexities govern covert signal amplitudes, guiding targeted optimization of feature engineering. The

show abstract

Section: Related Workmentioning

confidence: 99%

LinguTimeX: Explainable AI of Natural Language Detection in Leakage Information with Covert Timing Channels

Darwish,

Al-Eidi,

Al-Shorman

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

“…The majority of ML methods for CTC identification rely on statistical features of network traffic, like packets inter-arrival time the entropy [217] this overcomes the creation of effective CTC detectors by the use of deep learning algorithms, particularly LSTM, 1D-CNN, including the LSTM-CNN composite model. The serial data relating to traffic inter-arrival time was used to train the models [218]. By offering one Trusted Execution Environment (TEE) for applications utilizing hardware characteristics like Intel SGX, confidential computing seeks to safeguard the source code as well as data under usage, so ENCIDER uses the SGX computer programming model in analysis and infers probable timing observation points to identify timing along with cache side-channel vulnerability in SGX operations [219].…”

Section: Side Channel Protection Countermeasuresmentioning

confidence: 99%

Era of Sentinel Tech: Charting Hardware Security Landscapes Through Post-Silicon Innovation, Threat Mitigation and Future Trajectories

Srinivas,

Elango

2024

IEEE Access

View full text Add to dashboard Cite

To meet the demanding requirements of VLSI design, including improved speed, reduced power consumption, and compact architectures, various IP cores from trusted and untrusted platforms are often integrated into a single System-on-Chip (SoC). However, this convergence poses a significant security challenge, as adversaries can exploit it to extract unauthorized information, compromise system performance, and obtain secret keys. Meanwhile, traditional CMOS features have limitations in addressing hardware vulnerabilities and security threats, so promising post-silicon technologies offer potential solutions. Beyond-CMOS technologies offer avenues to fortify hardware security through distinct physical properties and nontraditional computing paradigms. These advancements bolster authentication processes, enhance key generation mechanisms, ensure hardware integrity and fortify resilience against side-channel attacks, hardware Trojans and quantum-resistant cryptography in securing hardware systems. This article provides a detailed review of hardware security, encompassing the identification and mitigation of threats, the implementation of robust countermeasures, the utilization of innovative primitives, countermeasures, various methodologies and distinct features offered by emerging technologies to resist hardware threats.Moreover, strategies to address challenges, explore future directions, and outline plans for achieving further research outcomes have been put forth in this field.

show abstract

Exploring low-level statistical features of n-grams in phishing URLs: a comparative analysis with high-level features

Tashtoush,

Alajlouni,

Albalas

et al. 2024

Cluster Comput

View full text Add to dashboard Cite

A deep learning approach for detecting covert timing channel attacks using sequential data

Cited by 3 publications

References 20 publications

LinguTimeX: Explainable AI of Natural Language Detection in Leakage Information with Covert Timing Channels

LinguTimeX: Explainable AI of Natural Language Detection in Leakage Information with Covert Timing Channels

Era of Sentinel Tech: Charting Hardware Security Landscapes Through Post-Silicon Innovation, Threat Mitigation and Future Trajectories

Exploring low-level statistical features of n-grams in phishing URLs: a comparative analysis with high-level features

Contact Info

Product

Resources

About