Toluwani Aremu

ReACT-CLIP: Response-Aware Test-Time Defense for Vision--Language Models

This work introduces ReACT-CLIP, a response-conditioned test-time defense that separately determines how strongly each input should be corrected and whether defensive intervention is necessary, and quantifies this variation using a prediction-instability score computed by Jensen--Shannon divergence and combines it with relative cross-noise drift to form the defensive intervention score.