3 papers
cs.CR2026
BackFlush: Knowledge-Free Backdoor Detection and Elimination with Watermark Preservation in Large Language Models
Jagadeesh Rachapudi, Ritali Vatsi, Pranav Singh +2
In recent trends, one can observe Large Language Models (LLMs) are exposed to backdoor attacks where vicious triggers added during training or model editing to elicit harmful outpu…
cs.AI2026
RePAIR: Interactive Machine Unlearning through Prompt-Aware Model Repair
Jagadeesh Rachapudi, Pranav Singh, Ritali Vatsi +2
Large language models (LLMs) inherently absorb harmful knowledge, misinformation, and personal data during pretraining on large-scale web corpora, with no native mechanism for sele…
cs.LG2026
BID-LoRA: A Parameter-Efficient Framework for Continual Learning and Unlearning
Jagadeesh Rachapudi, Ritali Vatsi, Praful Hambarde +1
Recent advances in deep learning underscore the need for systems that can not only acquire new knowledge through Continual Learning (CL) but also remove outdated, sensitive, or pri…