Wenjia Song

Publications

Wenjia Song, Ya Xiao, Jingyuan Qi, Nathan Dautenhahn, Na Meng, Elena Ferrari, Danfeng (Daphne) Yao.
Crypto-ransomware Detection through Quantitative API-based Behavioral Profiling. [Submitted]

• Ransomware attacks have had a resurgence in recent years. Our project aims to characterize ransomware behaviors and identify security gaps by experimentally measuring ransomware executions, evaluating different existing detection and recovery strategies, and pointing out future directions for improving detection.

Sharmin Afrose*, Wenjia Song*, Charles B. Nemeroff, Chang Lu, Danfeng (Daphne) Yao.
(*Contributed equally)
Subpopulation-specific Machine Learning Prognosis for Underrepresented Patients with Double Prioritized Bias Correction.
Communications Medicine. 2022

• This project identifies the hidden problem that many seemingly good machine learning prognosis models tend to perform poorly on minority groups due to the imbalance of clinical datasets. We further propose a double prioritized correction to improve the model performance for the minority prediction class and minority demographic groups.

Wenjia Song and Danfeng (Daphne) Yao.
Poster: APT Detection through Sensitive File Access Monitoring.
The Network and Distributed System Security (NDSS) Symposium 2022.

Ya Xiao, Wenjia Song, Jingyuan Qi, Bimal Viswanath, Patrick McDaniel, Danfeng (Daphne) Yao.
Specializing Neural Networks for Cryptographic Code Completion Applications.
IEEE Transactions on Software Engineering. 2023.

• This project comprehensively compares the neural-network-based methodologies to model Java security API usage. We design the program-analysis-guided embedding strategies to produce the dependence-aware code embedding and develop a learning-based code suggestion engine to suggest the correct API usage based on multiple data dependence paths extracted by program analysis.

Activities

Student mentoring    

• Sahithi Sarva and Aneka Busam (undergraduate) at UR2PHD program on a ransomware detection project

• Sanjula Karanam (M.S.) on a ransomware analysis and detection project.

• Lifan Ren (undergraduate) on malware analysis and reverse engineering.

• Alex Owens (undergraduate) on advanced persistent threat (APT) data analysis.

Web administrator for Individualized Cybersecurity Research Mentoring (iMentor) Workshop

• Held with ACM Conference on Computer and Communications Security (ACM CCS)

• 1st workshop at ACM CCS 2020 and 2nd at ACM CCS 2021

• iMentor workshop mentored and career-advised early-stage graduate students from underrepresented communities who want to pursue a career in computer security.

Web administrator for Workshop for Women in Cybersecurity Research (CyberW)

• Held with ACM Conference on Data and Application Security and Privacy (ACM CODASPY 2020).

• CyberW workshop gathered underrepresented cybersecurity professionals, students, and researchers to attend top security and privacy conferences and engage in cutting-edge security and privacy research.