Nahom M Birhan

Nahom M Birhan

Research Assistant- (ECE)- AI Security

Currently working as a Research Assistant at Old Dominion University, actively engaged in research on jailbreak and backdoor attacks and defenses in large language models (LLMs) and multimodal language model settings. I am a Machine Learning and AI Software Engineer with over five years of professional experience, specializing in applied machine learning for cybersecurity.

I am committed to ethical AI development and the innovative application of machine learning in the field of security.

Research Interests

My research focuses on the intersection of machine learning, artificial intelligence, and cybersecurity, with a particular emphasis on leveraging ML for cybersecurity applications and exploring the robustness and vulnerabilities of ML models. I'm interested in developing lightweight ML solutions for edge devices and IoT environments, addressing challenges in network security, anomaly detection, and impostor identification. My work extends to investigating email phishing detection, blockchain applications in healthcare data security, and novel ML applications in environmental monitoring. Through this research, I aim to enhance the security and efficiency of AI systems while deepening our understanding of their potential vulnerabilities and limitations in real-world, resource-constrained scenarios.

Research Areas

Machine Learning in CybersecurityAI Model RobustnessML VulnerabilitiesEdge Computing and securityIoT SecurityNetwork Anomaly/Imposter DetectionBlockchain and Cryptography in Healthcare

Research Projects

Jailbreak and Backdoor Attacks in LLMs and Multimodal LMs

Actively working on this research, not published yet

Impostor Detection in IoT Edge Sensor Networks

Developed lightweight LSTM model for edge devices, optimized using TensorFlow Lite quantization

Technologies: Raspberry PI, Arduino nano 33 BLE, TensorFlow/Lite, Python, C/C++

Email Phishing Detection in Africa

Analyzed African-specific phishing patterns, implemented and compared five ML models, mitigated overfitting

Technologies: Scikit-learn, TensorFlow, Numpy

Blockchain-Based Healthcare Data Security

Proposed system integrating blockchain and IPFS for secure medical records, compared IPFS and Amazon S3 access times.

Technologies: IPFS, AWS (IAM, S3), Blockchain concepts

Prime and Composite Classification

Created dataset of 2 million numbers, developed models using sequence models and 1D-CNN, analyzed performance

Technologies: Python, TensorFlow, NumPy, Google Colab

Smart Irrigation System (BSc. research)

Designed automated system with XBee sensor communication, integrated motors, pumps, and sensors, developed control algorithms

Technologies: Proteus, XBee, Arduino, C/C++, Various sensors