3 papers
cs.AI2026
Are You Reading the Right Thing? Rethinking Internal Signals for Prompt-Injection Detection
Sarthak Gupta, Priyanka Tembey
Several recent studies propose detecting prompt injections from a language model's internal state. However, these methods do not measure a single security property. Residual-stream…
cs.LG2025
Pruning as a Defense: Reducing Memorization in Large Language Models
Mansi Gupta, Nikhar Waghela, Sarthak Gupta +2
Large language models have been shown to memorize significant portions of their training data, which they can reproduce when appropriately prompted. This work investigates the impa…
cs.CV2022
[Re] Distilling Knowledge via Knowledge Review
Apoorva Verma, Pranjal Gulati, Sarthak Gupta
This effort aims to reproduce the results of experiments and analyze the robustness of the review framework for knowledge distillation introduced in the CVPR '21 paper 'Distilling…