Fully automated AI spear phishing achieved a 54% click-through rate on 101 human participants, matching human experts and far exceeding a 12% control rate.
IBM finds that ChatGPT can generate phishing emails nearly as convincing as a human | VentureBeat
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Evaluating Large Language Models' Capability to Launch Fully Automated Spear Phishing Campaigns: Validated on Human Subjects
Fully automated AI spear phishing achieved a 54% click-through rate on 101 human participants, matching human experts and far exceeding a 12% control rate.