Pankayaraj Pathmanathan

Most-cited papers

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

   Pankayaraj Pathmanathan, Souradip Chakraborty, Xiangyu Liu, Yongyuan Liang +1 more

   2024arXiv.org37 citations

   Semantic Scholar

   Save

2. Can Watermarking Large Language Models Prevent Copyrighted Text Generation and Hide Training Data?

   Michael-Andrei Panaitescu-Liess, Zora Che, Bang An, Yuancheng Xu +5 more

   2024AAAI Conference on Artificial Intelligence28 citations

   Semantic Scholar

   Save

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

   Pankayaraj Pathmanathan, Souradip Chakraborty, Xiangyu Liu, Yongyuan Liang +1 more

   2025AAAI Conference on Artificial Intelligence9 citations Open access

   Semantic Scholar

   Save

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

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

   2025arXiv.org7 citations

   Semantic Scholar

   Save

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

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

   2024arXiv.org6 citations

   Semantic Scholar

   Save

6. PoisonedParrot: Subtle Data Poisoning Attacks to Elicit Copyright-Infringing Content from Large Language Models

   Michael-Andrei Panaitescu-Liess, Pankayaraj Pathmanathan, Yiğitcan Kaya, Zora Che +4 more

   2025North American Chapter of the Association for Computational Linguistics3 citations

   Semantic Scholar

   Save

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

   Pankayaraj Pathmanathan, Fu-Rong Huang

   2026arXiv.org2 citations

   Semantic Scholar

   Save

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

   Pankayaraj Pathmanathan, Furong Huang

   2025Annual Meeting of the Association for Computational Linguistics2 citations Open access

   Semantic Scholar

   Save

9. Compliance2LoRA: On-Demand Safety Alignment on Arbitrary Policy Subsets via Hypernetwork-Generated LoRA Adapters

   Pankayaraj Pathmanathan, Furong Huang

   2026arXiv.org1 citations

   Semantic Scholar

   Save

10. 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 +1 more

    2026AAAI Conference on Artificial Intelligence1 citations Open access

    Semantic Scholar

    Save

11. Using Curiosity for an Even Representation of Tasks in Continual Offline Reinforcement Learning

    Pankayaraj Pathmanathan, N. Díaz-Rodríguez, J. del Ser

    2023Cognitive Computation1 citations Open access

    Semantic Scholar

    Save

12. Reinforcement Learning Based Autonomous Quadcopter Control - Semester 7 Report -

    Pankayaraj Pathmanathan, Chandima Samarasinghe, Y. Sumanasekera

    20201 citations

    Semantic Scholar

    Save

13. Compliance2LoRA: Personalizable On-Demand Safety Alignment on Arbitrary Policy Subsets via Hypernetwork-Generated LoRA Adapters

    Pankayaraj Pathmanathan, Furong Huang

    20260 citations

    Semantic Scholar

    Save

14. Poisson Processes Stochastic Processes Project

    Pankayaraj Pathmanathan

    20200 citations

    Semantic Scholar

    Save