← Search

Nikhil Reddy Billa

2 accepted papers

2026

Adversarial Déjà Vu: Jailbreak Dictionary Learning for Stronger Generalization to Unseen Attacks

ICLR 2026poster

Large language models remain vulnerable to jailbreak attacks that bypass safety guardrails to elicit harmful outputs. Defending against novel jailbreaks represents a critical challenge in AI safety. Adversarial training---designed to make models robust against worst-case perturbations---has been the…

Cited by 0SourceScholar
2025

Retracing the Past: LLMs Emit Training Data When They Get Lost

EMNLP 2025

The memorization of training data in large language models (LLMs) poses significant privacy and copyright concerns. Existing data extraction methods, particularly heuristic-based divergence attacks, often exhibit limited success and offer limited insight into the fundamental drivers of memorization

Cited by 0SourcePDFScholar