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: ICLR (2024)

Keyphrases

countermeasures
information retrieval
malicious users
multi agent
neural network
information systems
lightweight
dos attacks
detection mechanism
malicious attacks
power analysis
key exchange protocol