Is LLM-as-a-Judge Robust? Investigating Universal Adversarial Attacks on Zero-shot LLM Assessment.

Vyas Raina Adian Liusie Mark J. F. Gales

Published in: CoRR (2024)

Keyphrases

image watermarking
information systems
learning environment
digital image watermarking
database
neural network
signal processing
computationally efficient
parameter tuning
traffic analysis
turing machine
malicious attacks