ROBAD combines a transformer encoder-decoder with contrastive adversarial training to detect bad actors from user post sequences, achieving higher F1 and lower F1 drop under next-post attacks than baselines.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
ROBAD: Robust Adversary-aware Local-Global Attended Bad Actor Detection Sequential Model
ROBAD combines a transformer encoder-decoder with contrastive adversarial training to detect bad actors from user post sequences, achieving higher F1 and lower F1 drop under next-post attacks than baselines.