Pankayaraj Pathmanathan

According to our database, Pankayaraj Pathmanathan authored at least 10 papers between 2024 and 2026.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2026

Deliberative Alignment is Deep, but Uncertainty Remains: Inference time safety improvement in reasoning via attribution of unsafe behavior to base model.

Pankayaraj Pathmanathan, Furong Huang

CoRR, April, 2026

Teach a Reward Model to Correct Itself: Reward Guided Adversarial Failure Discovery for Robust Reward Modeling.

Pankayaraj Pathmanathan, Furong Huang

Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2026

AdvBDGen: A Robust Framework for Generating Adaptive and Stealthy Backdoors in LLM Alignment.

Pankayaraj Pathmanathan, Udari Madhushani Sehwag, Michael-Andrei Panaitescu-Liess, Cho-Yu Jason Chiang, Furong Huang

Proceedings of the Fortieth AAAI Conference on Artificial Intelligence, 2026

2025

RAGPart & RAGMask: Retrieval-Stage Defenses Against Corpus Poisoning in Retrieval-Augmented Generation.

Pankayaraj Pathmanathan, Michael-Andrei Panaitescu-Liess, Cho-Yu Jason Chiang, Furong Huang

CoRR, December, 2025

Reward Models Can Improve Themselves: Reward-Guided Adversarial Failure Mode Discovery for Robust Reward Modeling.

Pankayaraj Pathmanathan, Furong Huang

CoRR, July, 2025

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

Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies, 2025

Is Poisoning a Real Threat to DPO? Maybe More So Than You Think.

Pankayaraj Pathmanathan, Souradip Chakraborty, Xiangyu Liu, Yongyuan Liang, Furong Huang

Proceedings of the Thirty-Ninth AAAI Conference on Artificial Intelligence, 2025

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

Proceedings of the Thirty-Ninth AAAI Conference on Artificial Intelligence, 2025

2024

AdvBDGen: Adversarially Fortified Prompt-Specific Fuzzy Backdoor Generator Against LLM Alignment.

Pankayaraj Pathmanathan, Udari Madhushani Sehwag, Michael-Andrei Panaitescu-Liess, Furong Huang

CoRR, 2024

Is poisoning a real threat to LLM alignment? Maybe more so than you think.

Pankayaraj Pathmanathan, Souradip Chakraborty, Xiangyu Liu, Yongyuan Liang, Furong Huang

CoRR, 2024