Yash Sinha
3 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
The paper demonstrates that autonomous web agents are highly susceptible to social-engineering attacks, leaking critical PII even when they internally flag a site as suspicious, necessitating output-level interception defenses.
The paper demonstrates that autonomous web agents are highly susceptible to social-engineering attacks, leaking critical PII even when they internally flag a site as suspicious, necessitating output-level interception defenses.
PURGE is a novel machine unlearning algorithm that leverages the duality between continual learning and unlearning to achieve high data retention while making the unlearned model indistinguishable from a model retrained from scratch.
Papers
PURGE: Projected Unlearning via Retain-Guided Erasure
PURGE is a novel machine unlearning algorithm that leverages the duality between continual learning and unlearning to achieve high data retention while making the unlearned model indistinguishable fro…