Diffusion models are generative models, which gradually add and remove noise to learn the
underlying distribution of training data for data generation. The components of diffusion …

The robustness of neural networks against input perturbations with bounded magnitude
represents a serious concern in the deployment of deep learning models in safety-critical …

Large language models (LLMs) are vulnerable to adversarial attacks that can bypass their
safety guardrails. In many domains, adversarial training has proven to be one of the most …

Current research in adversarial robustness of LLMs focuses on discrete input manipulations
in the natural language space, which can be directly transferred to closed-source models …

In mobile robotics, perception in uncontrolled environments like autonomous driving is a
central hurdle. Existing active learning frameworks can help enhance perception by …

Over the years, researchers have developed myriad attacks that exploit the ubiquity of
adversarial examples, as well as defenses that aim to guard against the security …

Their vulnerability to small, imperceptible attacks limits the adoption of deep learning models
to real-world systems. Adversarial training has proven to be one of the most promising …

Despite extensive research since the community learned about adversarial examples 10
years ago, we still do not know how to train high-accuracy classifiers that are guaranteed to …

The rapid growth and widespread reliance on machine learning (ML) systems across critical
applications such as healthcare, autonomous driving, and cybersecurity have un-derscored …