Scholar
Poojitha Thota
Google Scholar ID: EESjWfsAAAAJ
PhD Student
Citations & Impact
Citations
258
H-index
6
i10-index
6
Publications
11
Co-authors
9
list available
Publications
Resume (English only)
Academic Achievements
- Recognized with several awards including the Distinguished Paper Award at IEEE S&P 2024 and the Johns Hopkins Suchman Outstanding Doctoral Student Award at UTA. Published multiple papers, such as 'From chatbots to phishbots?: Phishing scam generation in commercial large language models' (IEEE S&P 2024) and 'Attacks against Abstractive Text Summarization Models through Lead Bias and Influence Functions' (EMNLP 2024).
Research Experience
- Interned twice at Google's Responsible AI team, working on improving the safety of Gemini models through multi-agent frameworks and adversarial prompt detection. Before PhD, worked as a Graduate Engineer at Hyundai Mobis, developing parking application software.
Education
- PhD Candidate in Computer Science and Engineering at the University of Texas at Arlington, advised by Dr. Shirin Nilizadeh; Received Master's degree in Computer Science and Bachelor's degree in Electronics & Communication.
Background
- Research interests include security and privacy in AI systems, particularly vulnerabilities of large language and vision-language models. Works on understanding how these systems can be exploited through adversarial attacks and data poisoning, and developing robust defenses against such threats. Research spans applications from text summarization to medical imaging, aiming to build more trustworthy and secure AI systems for real-world deployment.
Miscellany
- Always open to research collaborations and happy to chat about AI security and privacy.
