An LLM can Fool Itself: A Prompt-Based Adversarial Attack.

Xilie Xu Keyi Kong Ning Liu Lizhen Cui Di Wang Jingfeng Zhang Mohan S. Kankanhalli

Published in: CoRR (2023)

Keyphrases

data mining
multi agent
countermeasures
secret key
neural network
social networks
ddos attacks
malicious users
bayesian networks
search algorithm
power analysis
attack graph
abstract argumentation
data corruption
attack graphs