30 citations · 109 across the 66 of their papers we have counts for
5 papers · 1 filter
NeuroLip: An Event-driven Spatiotemporal Learning Framework for Cross-Scene Lip-Motion-based Visual Speaker Recognition
Junguang Yao, Wenye Liu, Stjepan Picek +1
Visual speaker recognition based on lip motion offers a silent, hands-free, and behavior-driven biometric solution that remains effective even when acoustic cues are unavailable. C…
Backdoor Directions in Vision Transformers
Sengim Karayalcin, Marina Krcek, Pin-Yu Chen +1
This paper investigates how Backdoor Attacks are represented within Vision Transformers (ViTs). By assuming knowledge of the trigger, we identify a specific ``trigger direction'' i…
Removing the Trigger, Not the Backdoor: Alternative Triggers and Latent Backdoors
Gorka Abad, Ermes Franch, Stefanos Koffas +1
Current backdoor defenses assume that neutralizing a known trigger removes the backdoor. We show this trigger-centric view is incomplete: \emph{alternative triggers}, patterns perc…
MIMIR: Masked Image Modeling for Mutual Information-based Adversarial Robustness
Xiaoyun Xu, Shujian Yu, Zhuoran Liu +1
Vision Transformers (ViTs) have emerged as a fundamental architecture and serve as the backbone of modern vision-language models. Despite their impressive performance, ViTs exhibit…
SoK: A Systematic Evaluation of Backdoor Trigger Characteristics in Image Classification
Gorka Abad, Jing Xu, Stefanos Koffas +3
Deep learning achieves outstanding results in many machine learning tasks. Nevertheless, it is vulnerable to backdoor attacks that modify the training set to embed a secret functio…