Showing cs.CVShow all
3 papers · 1 filter
cs.CV2025
CertMask: Certifiable Defense Against Adversarial Patches via Theoretically Optimal Mask Coverage
Xuntao Lyu, Ching-Chi Lin, Abdullah Al Arafat +3
Adversarial patch attacks inject localized perturbations into images to mislead deep vision models. These attacks can be physically deployed, posing serious risks to real-world app…
cs.CV2024
Fisher Information guided Purification against Backdoor Attacks
Nazmul Karim, Abdullah Al Arafat, Adnan Siraj Rakin +2
Studies on backdoor attacks in recent years suggest that an adversary can compromise the integrity of a deep neural network (DNN) by manipulating a small set of training samples. O…
cs.CV2024
Augmented Neural Fine-Tuning for Efficient Backdoor Purification
Nazmul Karim, Abdullah Al Arafat, Umar Khalid +2
Recent studies have revealed the vulnerability of deep neural networks (DNNs) to various backdoor attacks, where the behavior of DNNs can be compromised by utilizing certain types…