Alaaddin Goktug Ayar

Alaaddin Goktug Ayar

Auto-generated profile, based on publicly available information

Alaaddin Goktug Ayar

School of Computing and Informatics, University of Louisiana at Lafayette, Lafayette, LA, USA

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
12 June 2024
Verified
Conference Paper
Open access
AAAlaaddin Goktug Ayar
Alaaddin Goktug Ayar
SASercan Aygun
Sercan Aygun
MNM. Hassan Najafi
M. Hassan Najafi
MMMartin Margala
Martin Margala

29 June 2025
Verified
Conference Paper
Open access
AAAlaaddin Goktug Ayar
Alaaddin Goktug Ayar
SASercan Aygun
Sercan Aygun
MMMartin Margala
Martin Margala

21 November 2023 in IEEE Embedded Systems Letters
Verified
Journal Article
Closed access
AAAlaaddin Goktug Ayar
Alaaddin Goktug Ayar
ASAbdullah Sahruri
Abdullah Sahruri
SASercan Aygun
Sercan Aygun
MMMehran Shoushtari Moghadam
Mehran Shoushtari Moghadam
MNM. Hassan Najafi
M. Hassan Najafi
MMMartin Margala
Martin Margala
Detecting vulnerable code blocks has become a highly popular topic in computer-aided design, especially with the advancement of natural language processing (NLP). Analyzing Hardware Description Languages (HDL), such as Verilog, involves dealing with lengthy code. This study introduces an innovative identification of attack-vulnerable hardware by the use of opcode processing. Leveraging the advantage of architecturally-defined opcodes and expressing all operations at the beginning of each code line, the word processing problem is efficiently transformed into opcode processing. This research converts a benchmark dataset into an intermediary code stack, subsequently classifying secure and fragile codes using NLP techniques. The results reveal a framework that achieves up to 94% accuracy when employing sophisticated Convolutional Neural Networks (CNNs) architecture with extra embedding layers. Thus, it provides a means for users to quickly verify the vulnerability of their HDL code by inspecting a supervised learning model trained on the predefined vulnerabilities. It also supports the superior efficacy of opcode-based processing in Trojan detection by analyzing the outcomes derived from a model trained using the HDL dataset.


22 June 2026
Verified
Conference Paper
Open access
AAAlaaddin Goktug Ayar
Alaaddin Goktug Ayar
MMMartin Margala
Martin Margala
Deep neural networks deployed in real-world systems may produce unreliable predictions when encountering inputs outside the training distribution. Detecting such out-of-distribution (OOD) inputs during inference is therefore critical for reliable deployment. We propose a lightweight monitoring framework that observes intermediate neural network embeddings and detects abnormal inputs using hyperdimensional computing (HDC). The monitor converts embeddings into binary hypervectors via random projection and sign encoding, and evaluates distance to class prototypes using only XOR and population-count operations. Experiments using CIFAR-10 as the in-distribution dataset and SVHN and CIFAR-100 as OOD datasets show that the proposed method achieves strong detection performance with highly efficient binary computation.