7 papers
Multi-Channel Spread-Spectrum Code Watermarking
Soohyeon Choi, Debin Gao, Yue Duan
Attributing code to the large language model that produced it is essential for provenance, licensing, and misuse accountability, yet no deployed watermark meets this need. Generati…
Compositional Jailbreaking: An Empirical Analysis of Mutator Chain Interactions in Aligned LLMs
Reinelle Jan Bugnot, Soohyeon Choi, Hoon Wei Lim +1
Jailbreaking attacks on large language models pose a significant threat to AI safety by enabling the generation of harmful or restricted content. While prior work has explored both…
Security and Quality in LLM-Generated Code: A Multi-Language, Multi-Model Analysis
Mohammed Kharma, Soohyeon Choi, Mohammed AlKhanafseh +1
Artificial Intelligence (AI)-driven code generation tools are increasingly used throughout the software development lifecycle to accelerate coding tasks. However, the security of A…
A Comprehensive Analysis of Evolving Permission Usage in Android Apps: Trends, Threats, and Ecosystem Insights
Ali Alkinoon, Trung Cuong Dang, Ahod Alghuried +6
The proper use of Android app permissions is crucial to the success and security of these apps. Users must agree to permission requests when installing or running their apps. Despi…
Fishing for Phishers: Learning-Based Phishing Detection in Ethereum Transactions
Ahod Alghuried, Abdulaziz Alghamdi, Ali Alkinoon +3
Phishing detection on Ethereum has increasingly leveraged advanced machine learning techniques to identify fraudulent transactions. However, limited attention has been given to und…
Evaluating the Vulnerability of ML-Based Ethereum Phishing Detectors to Single-Feature Adversarial Perturbations
Ahod Alghuried, Ali Alkinoon, Abdulaziz Alghamdi +3
This paper explores the vulnerability of machine learning models to simple single-feature adversarial attacks in the context of Ethereum fraudulent transaction detection. Through c…