Smarter applications are making better use of the insights gleaned from data, having an
impact on every industry and research discipline. At the core of this revolution lies the tools …

Self-supervised learning (SSL) has recently achieved impressive performance on various
time series tasks. The most prominent advantage of SSL is that it reduces the dependence …

Large language models (LLMs) are vulnerable to adversarial attacks that add malicious
tokens to an input prompt to bypass the safety guardrails of an LLM and cause it to produce …

Recent work argues that robust training requires substantially larger datasets than those
required for standard classification. On CIFAR-10 and CIFAR-100, this translates into a …

Adversarial training suffers from robust overfitting, a phenomenon where the robust test
accuracy starts to decrease during training. In this paper, we focus on reducing robust …

Deep neural networks (DNNs) are known to be vulnerable to adversarial examples. It is thus
imperative to devise effective attack algorithms to identify the deficiencies of DNNs …

Transferability of adversarial examples is of central importance for attacking an unknown
model, which facilitates adversarial attacks in more practical scenarios, eg, blackbox attacks …

Adaptive attacks have (rightfully) become the de facto standard for evaluating defenses to
adversarial examples. We find, however, that typical adaptive evaluations are incomplete …

The study on improving the robustness of deep neural networks against adversarial
examples grows rapidly in recent years. Among them, adversarial training is the most …

Text-to-image diffusion models are nothing but a revolution, allowing anyone, even without
design skills, to create realistic images from simple text inputs. With powerful personalization …