Search Results for author:
Found 2 papers, 2 papers with code
PoisonedRAG: Knowledge Poisoning Attacks to Retrieval-Augmented Generation of Large Language Models
We formulate knowledge poisoning attacks as an optimization problem, whose solution is a set of poisoned texts.
Prompt Injection Attacks and Defenses in LLM-Integrated Applications
As a result, the literature lacks a systematic understanding of prompt injection attacks and their defenses.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
