GPT-assisted adversarial retraining restores LinkedIn fake-profile detectors from a 42-52 percent false accept rate on AI-written profiles to 1-7 percent.
Linkedin fake profile detection,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SI 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Weak Links in LinkedIn: Enhancing Fake Profile Detection in the Age of LLMs
GPT-assisted adversarial retraining restores LinkedIn fake-profile detectors from a 42-52 percent false accept rate on AI-written profiles to 1-7 percent.