Published:
A defense framework that disrupts semantic and gradient alignment across bit-widths to prevent patch transferability in quantized neural networks.
Published:
A stochastic differentiable defense framework that breaks gradient consensus via divergent responses across filtered transformations.
Published:
A framework that significantly improves black-box adversarial attack transferability from Vision Transformers via spectral and semantic regularization.
Published:
A dynamic adversarial patch that adapts spatially and temporally to effectively evade modern person detection models under realistic conditions.
