Pankayaraj Pathmanathan
5 papers · 2025–2026 · 3 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓
🌍
Conference Polyglot · Bronze
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(11)
⭐
Rising Star
(5)
❓
The Questioner
(2)
Top co-authors
Research topics
Keywords
copyright infringement
(2)
data poisoning
(2)
large language model
(2)
backdoor attack
(2)
adversarial attack
(2)
reward model
(1)
poisoning attack
(1)
human preference alignment
(1)
membership inference
(1)
membership inference attack
(1)
content generation
(1)
training data extraction
(1)
large language model alignment
(1)
adversarial fine-tuning
(1)
controlled decoding
(1)
reinforcement learning human feedback
(1)
model security
(1)
adversarial failure discovery
(1)
direct preference optimization
(1)
text generation
(1)
Papers
AdvBDGen: A Robust Framework for Generating Adaptive and Stealthy Backdoors in LLM Alignment
AAAI 2026
Teach a Reward Model to Correct Itself: Reward Guided Adversarial Failure Discovery for Robust Reward Modeling
ACL 2026
Can Watermarking Large Language Models Prevent Copyrighted Text Generation and Hide Training Data?
AAAI 2025
Is Poisoning a Real Threat to DPO? Maybe More So Than You Think
AAAI 2025
PoisonedParrot: Subtle Data Poisoning Attacks to Elicit Copyright-Infringing Content from Large Language Models
NAACL 2025