Pankayaraj Pathmanathan

5 papers at tracked venues · 4 at CORE A* · active 2025–2026

Venues

Furong Huang

×5

Michael-Andrei Panaitescu-Liess

×3

Zora Che

×2

Bang An

×2

Souradip Chakraborty

×2

Sicheng Zhu

×2

Udari Madhushani Sehwag

×1

Cho-Yu Jason Chiang

×1

Yuancheng Xu

×1

Tom Goldstein

×1

Xiangyu Liu

×1

Yongyuan Liang

×1

AdvBDGen: A Robust Framework for Generating Adaptive and Stealthy Backdoors in LLM Alignment
AAAI 2026 · Pankayaraj Pathmanathan,
Udari Madhushani Sehwag
,
Michael-Andrei Panaitescu-Liess
,
Cho-Yu Jason Chiang
,
Furong Huang
Teach a Reward Model to Correct Itself: Reward Guided Adversarial Failure Discovery for Robust Reward Modeling
ACL 2026 · Pankayaraj Pathmanathan,
Furong Huang
Can Watermarking Large Language Models Prevent Copyrighted Text Generation and Hide Training Data?
AAAI 2025 ·
Michael-Andrei Panaitescu-Liess
,
Zora Che
,
Bang An
,
Yuancheng Xu
, Pankayaraj Pathmanathan,
Souradip Chakraborty
,
Sicheng Zhu
,
Tom Goldstein
,
Furong Huang
Is Poisoning a Real Threat to DPO? Maybe More So Than You Think
AAAI 2025 · Pankayaraj Pathmanathan,
Souradip Chakraborty
,
Xiangyu Liu
,
Yongyuan Liang
,
Furong Huang
PoisonedParrot: Subtle Data Poisoning Attacks to Elicit Copyright-Infringing Content from Large Language Models
NAACL 2025 ·
Michael-Andrei Panaitescu-Liess
, Pankayaraj Pathmanathan,
Yigitcan Kaya
,
Zora Che
,
Bang An
,
Sicheng Zhu
,
Aakriti Agrawal
,
Furong Huang