Adaptive defenses, which optimize at test time, promise to improve adversarial robustness.
We categorize such adaptive test-time defenses, explain their potential benefits and …

Adversarial examples that can fool neural network classifiers have attracted much attention.
Existing approaches to detect adversarial examples leverage a supervised scheme in …

Adversarial purification is a kind of defense technique that can defend various unseen
adversarial attacks without modifying the victim classifier. Existing methods often depend on …

Existing adversarial example defense methods are static, meaning they remain unchanged
once training is completed, regardless of how attack methods change. Consequently, static …

In recent years, diffusion models (DMs) have drawn significant attention for their success in
approximating data distributions, yielding state-of-the-art generative results. Nevertheless …

We propose a novel and low-cost test-time adversarial defense by devising interpretability-
guided neuron importance ranking methods to identify neurons important to the output …

Keyless entry systems in cars are adopting neural networks for localizing its operators.
Using test-time adversarial defences equip such systems with the ability to defend against …

Adversarial attacks meticulously generate minuscule, imperceptible perturbations that add to
images to deceive neural networks. Adversarial purification methods seek to remove …

Accurately evaluating the defense models against adversarial examples has been proven to
be a challenging task. We have recognized the limitations of mainstream evaluation …

Accurately evaluating the defense models against adversarial examples has been proven to
be a challenging task. We have recognized the limitations of mainstream evaluation …