Pankayaraj Pathmanathan

PhD student, Department of Computer Science, University of Maryland, College Park

Joined

May 2023

Names

Pankayaraj Pathmanathan (Preferred)

Emails

****@gmail.com (Confirmed)

****@umd.edu (Confirmed)

****@gmail.com (Confirmed)

Personal Links

Career & Education History

PhD student

Department of Computer Science , University of Maryland, College Park (umd.edu)

2022 – 2027

Advisors, Relations & Conflicts

PhD Advisor

Furong Huang

2022 – 2027

Expertise

No areas of expertise listed

Publications

Teach a Reward Model to Correct Itself: Reward Guided Adversarial Failure Discovery for Robust Reward Modeling
Pankayaraj Pathmanathan, Furong Huang
- ICLR 2026 Conference Withdrawn Submission
- Readers: Everyone
AdvBDGen: A Robust Framework for Generating Adaptive and Stealthy Backdoors in LLM Alignment Attacks
Pankayaraj Pathmanathan, Udari Madhushani Sehwag, Michael-Andrei Panaitescu-Liess, Furong Huang
- BuildingTrust
- Readers: Everyone
PoisonedParrot: Subtle Data Poisoning Attacks to Elicit Copyright-Infringing Content from Large Language Models
Michael-Andrei Panaitescu-Liess, Pankayaraj Pathmanathan, Yigitcan Kaya, Zora Che, Bang An, Sicheng Zhu, Aakriti Agrawal, Furong Huang
- SafeGenAi Poster
- Readers: Everyone
AdvBDGen: Adversarially Fortified Prompt-Specific Fuzzy Backdoor Generator Against LLM Alignment
Pankayaraj Pathmanathan, Udari Madhushani Sehwag, Michael-Andrei Panaitescu-Liess, Furong Huang
- SafeGenAi Poster
- Readers: Everyone
AdvBDGen: Adversarially Fortified Prompt-Specific Fuzzy Backdoor Generator Against LLM Alignment
Pankayaraj Pathmanathan, Udari Madhushani Sehwag, Michael-Andrei Panaitescu-Liess, Furong Huang
- Submitted to ICLR 2025
- Readers: Everyone
Can Watermarking Large Language Models Prevent Copyrighted Text Generation and Hide Training Data?
Michael-Andrei Panaitescu-Liess, Zora Che, Bang An, Yuancheng Xu, Pankayaraj Pathmanathan, Souradip Chakraborty, Sicheng Zhu, Tom Goldstein, Furong Huang
- AdvML-Frontiers 2024
- Readers: Everyone
Can Watermarking Large Language Models Prevent Copyrighted Text Generation and Hide Training Data?
Michael-Andrei Panaitescu-Liess, Zora Che, Bang An, Yuancheng Xu, Pankayaraj Pathmanathan, Souradip Chakraborty, Sicheng Zhu, Tom Goldstein, Furong Huang
- NextGenAISafety 2024 Poster
- Readers: Everyone
Is poisoning a real threat to LLM alignment? Maybe more so than you think
Pankayaraj Pathmanathan, Souradip Chakraborty, Xiangyu Liu, Yongyuan Liang, Furong Huang
- ICML 2024 Workshop MHFAIA Poster
- Readers: Everyone
SDM-RL: Steady-State Divergence Maximization for Robust Reinforcement Learning
Pankayaraj Pathmanathan, Furong Huang
- Submitted to ICLR 2024
- Readers: Everyone