Hi! I’m Sifat Muhammad Abdullah, a 3rd year Ph.D. student at the Department of Computer Science, Virginia Tech. I am advised by Dr. Bimal Viswanath. My research interests center around the security of machine learning models. Particularly, I focus on uncovering the vulnerabilities of deepfake content detectors using foundation models and developing more robust and generalizable methods for their detection. I have received my Bachelor’s degree in Computer Science from BUET in April, 2019.
Please contact me with any questions (email on the left).
Publications
A First Look at Toxicity Injection Attacks on Open-domain ChatbotsAravind Cheruvu, Connor Weeks, Sifat Muhammad Abdullah, Shravya Kanchi, Danfeng Yao, Bimal Viswanath.
ACSAC
Austin, Texas, Dec 2023.
Deepfake Text Detection: Limitations and Opportunities
Jiameng Pu, Zain Sarwar, Sifat Muhammad Abdullah, Abdullah Rehman, Yoonjin Kim, Parantapa Bhattacharya, Mobin Javed, Bimal Viswanath.
IEEE S&P (Oakland)
San Francisco, CA, May 2023.
PDF Code and Dataset Video
CHAPAO: Likelihood and hierarchical reference-based representation of biomolecular sequences and applications to compressing multiple sequence alignments
Md Ashiqur Rahman, Abdullah Aman Tutul, Sifat Muhammad Abdullah, Md Shamsuzzoha Bayzid.
PLOS ONE Journal, 2022.
PDF Code and Dataset
A Web-Based System for Efficient Contact Tracing Query in a Large Spatio-Temporal Database
Shadman Saqib Eusuf, Kazi Ashik Islam, Mohammed Eunus Ali, Sifat Muhammad Abdullah, Abdus Salam Azad.
SIGSPATIAL
Seattle, WA, Nov 2020.
Recent News
- [Oct 2023] - Presented my work on ways to integrate Generative AI to your benefit at VT Skillshop Series - Leveraging Creative Technologies.
- [Oct 2023] - Our Lab was featured in "The Dark Side of AI" by VPM News.
- [Oct 2023] - Student Spotlight by Commonwealth Cyber Initiative (CCI).
- [June 2022] - Our paper on "A First Look at Toxicity Injection Attacks on Open-domain Chatbots" was accepted at ACSAC 2023.
- [July 2023] - Our paper titled "Deepfake Text Detection: Limitations and Opportunities" was featured in Communications of the ACM.
- [Nov 2022] - Our paper titled "Deepfake Text Detection: Limitations and Opportunities" was featured in TechXplore.
- [June 2022] - Our paper on "Deepfake Text Detection: Limitations and Opportunities" was accepted at IEEE S&P 2023.