Search Results for author:
Found 5 papers, 2 papers with code
Exploiting the Layered Intrinsic Dimensionality of Deep Models for Practical Adversarial Training
Despite being a heavily researched topic, Adversarial Training (AT) is rarely, if ever, deployed in practical AI systems for two primary reasons: (i) the gained robustness is frequently accompanied by a drop in generalization and (ii) generating adversarial examples (AEs) is computationally prohibitively expensive.
A3T: Accuracy Aware Adversarial Training
Adversarial training has been empirically shown to be more prone to overfitting than standard training.
Impact of Adversarial Training on Robustness and Generalizability of Language Models
Specifically, we study the effect of pre-training data augmentation as well as training time input perturbations vs. embedding space perturbations on the robustness and generalization of transformer-based language models.
PRNU Estimation from Encoded Videos Using Block-Based Weighting
Estimating the photo-response non-uniformity (PRNU) of an imaging sensor from videos is a challenging task due to complications created by several processing steps in the camera imaging pipeline.
Image and Video Processing Cryptography and Security
Source Camera Verification from Strongly Stabilized Videos
Image stabilization performed during imaging and/or post-processing poses one of the most significant challenges to photo-response non-uniformity based source camera attribution from videos.
