DP-Net uses a DDPG reinforcement-learning agent to dynamically tune Gaussian perturbation of embeddings, improving average cross-domain accuracy and adversarial robustness of AI-generated text detection.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Kill two birds with one stone: generalized and robust AI-generated text detection via dynamic perturbations
DP-Net uses a DDPG reinforcement-learning agent to dynamically tune Gaussian perturbation of embeddings, improving average cross-domain accuracy and adversarial robustness of AI-generated text detection.