Diffusion-based purification defenses leverage diffusion models to remove crafted
perturbations of adversarial examples and achieve state-of-the-art robustness. Recent …

The score-based query attacks (SQAs) pose practical threats to deep neural networks by
crafting adversarial perturbations within dozens of queries, only using the model's output …

Evaluating robustness of machine-learning models to adversarial examples is a challenging
problem. Many defenses have been shown to provide a false sense of robustness by …

Based on the significant improvement of model robustness by AT (Adversarial Training),
various variants have been proposed to further boost the performance. Well-recognized …

Adversarial attacks based on randomized search schemes have obtained state-of-the-art
results in black-box robustness evaluation recently. However, as we demonstrate in this …

The phenomenon of adversarial examples has been revealed in variant scenarios. Recent
studies show that well-designed adversarial defense strategies can improve the robustness …

Adversarial training has been considered to be one of the most effective strategies to defend
against adversarial attacks. Most existing adversarial training methods have shown a trade …

Adversarial examples, inputs designed to induce worst-case behavior in machine learning
models, have been extensively studied over the past decade. Yet, our understanding of this …

Deep neural network (DNN) accelerators received considerable attention in recent years
due to the potential to save energy compared to mainstream hardware. Low-voltage …

Despite the widespread use of deep learning algorithms, vulnerability to adversarial attacks
is still an issue limiting their use in critical applications. Detecting these attacks is thus crucial …