Recent studies have demonstrated the susceptibility of deep neural networks to backdoor
attacks. Given a backdoored model, its prediction of a poisoned sample with trigger will be …

Backdoor defense, which aims to detect or mitigate the effect of malicious triggers introduced
by attackers, is becoming increasingly critical for machine learning security and integrity …

Abstract Vision Transformer (ViT), as a powerful alternative to Convolutional Neural Network
(CNN), has received much attention. Recent work showed that ViTs are also vulnerable to …

Deep neural networks (DNNs) have been shown to be vulnerable to adversarial examples,
which can produce erroneous predictions by injecting imperceptible perturbations. In this …

Fast adversarial training (FAT) effectively improves the efficiency of standard adversarial
training (SAT). However, initial FAT encounters catastrophic overfitting, ie, the robust …

Decision-based attack poses a severe threat to real-world applications since it regards the
target model as a black box and only accesses the hard prediction label. Great efforts have …

Instruction tuning enhances large vision-language models (LVLMs) but raises security risks
through potential backdoor attacks due to their openness. Previous backdoor studies focus …

Deep learning-based lane detection (LD) plays a critical role in autonomous driving
systems, such as adaptive cruise control. However, it is vulnerable to backdoor attacks …

Recent studies have shown that detectors based on deep models are vulnerable to
adversarial examples, even in the black-box scenario where the attacker cannot access the …

Adversarial attack methods based on point manipulation for 3D point cloud classification
have revealed the fragility of 3D models yet the adversarial examples they produce are …