5 papers
Steering Code LLMs with Activation Directions for Language and Library Control
Md Mahbubur Rahman, Arjun Guha, Harshitha Menon
Code LLMs often default to particular programming languages and libraries under neutral prompts. We investigate whether these preferences are encoded as approximately linear direct…
ConceptCoder: Improve Code Reasoning via Concept Learning
Md Mahbubur Rahman, Hengbo Tong, Wei Le
Large language models (LLMs) have shown promising results for software engineering applications, but still struggle with code reasoning tasks such as vulnerability detection (VD).…
Elevating Intrusion Detection and Security Fortification in Intelligent Networks through Cutting-Edge Machine Learning Paradigms
Md Minhazul Islam Munna, Md Mahbubur Rahman, Jaroslav Frnda +2
The proliferation of IoT devices and their reliance on Wi-Fi networks have introduced significant security vulnerabilities, particularly the KRACK and Kr00k attacks, which exploit…
InstructNet: A Novel Approach for Multi-Label Instruction Classification through Advanced Deep Learning
Tanjim Taharat Aurpa, Md Shoaib Ahmed, Md Mahbubur Rahman +1
People use search engines for various topics and items, from daily essentials to more aspirational and specialized objects. Therefore, search engines have taken over as peoples pre…
To Err is Machine: Vulnerability Detection Challenges LLM Reasoning
Benjamin Steenhoek, Md Mahbubur Rahman, Monoshi Kumar Roy +5
In this paper, we present a challenging code reasoning task: vulnerability detection. Large Language Models (LLMs) have shown promising results in natural-language and math reasoni…