Related papers: Systematically Evaluation of Challenge Obfuscated …

Existing defenses against adversarial attacks are typically tailored to a specific perturbation type. Using adversarial training to defend against multiple types of perturbation requires expensive adversarial examples from different…

Data-driven deep learning (DL) techniques developed for automatic modulation classification (AMC) of wireless signals are vulnerable to adversarial attacks. This poses a severe security threat to the DL-based wireless systems, specifically…

The Pickup and Delivery Problem (PDP) is a fundamental and challenging variant of the Vehicle Routing Problem, characterized by tightly coupled pickup--delivery pairs, precedence constraints, and spatial layouts that often exhibit…

As we seek to deploy machine learning models beyond virtual and controlled domains, it is critical to analyze not only the accuracy or the fact that it works most of the time, but if such a model is truly robust and reliable. This paper…

We propose a new defense mechanism against adversarial attacks inspired by an optical co-processor, providing robustness without compromising natural accuracy in both white-box and black-box settings. This hardware co-processor performs a…

It has been demonstrated that very simple attacks can fool highly-sophisticated neural network architectures. In particular, so-called adversarial examples, constructed from perturbations of input data that are small or imperceptible to…

Image restoration schemes based on the pre-trained deep models have received great attention due to their unique flexibility for solving various inverse problems. In particular, the Plug-and-Play (PnP) framework is a popular and powerful…

Machine Learning Interatomic Potentials (MLIPs) achieve near ab initio accuracy at a fraction of the cost of quantum-mechanical simulations, yet they remain prone to silent failures on out-of-distribution configurations, making principled…

The last six years have witnessed significant progress in adversarially robust deep learning. As evidenced by the CIFAR-10 dataset category in RobustBench benchmark, the accuracy under $\ell_\infty$ adversarial perturbations improved from…

Prompt injection attacks pose significant risks to language model safety, yet existing defenses are typically evaluated using classification performance. We show that high detection performance does not imply representational robustness.…

Point clouds are extensively employed in a variety of real-world applications such as robotics, autonomous driving and augmented reality. Despite the recent success of point cloud neural networks, especially for safety-critical tasks, it is…

Deep learning models are widely employed in safety-critical applications yet remain susceptible to adversarial attacks -- imperceptible perturbations that can significantly degrade model performance. Conventional defense mechanisms…

Collision avoidance is a problem largely studied in robotics, particularly in unmanned aerial vehicle (UAV) applications. Among the main challenges in this area are hardware limitations, the need for rapid response, and the uncertainty…

Deep neural networks demonstrate impressive performance in visual recognition, but they remain vulnerable to adversarial attacks that is imperceptible to the human. Although existing defense strategies such as adversarial training and…

A learned Bloom filter (LBF) combines a classical Bloom filter (CBF) with a learning model to reduce the amount of memory needed to represent a given set while achieving a target false positive rate (FPR). Provable security against adaptive…

Dynamic partial reconfiguration (DPR) allows one region of an field-programmable gate array (FPGA) fabric to be reconfigured without affecting the operations on the rest of the fabric. To use an FPGA as a dynamically shared compute…

Federated Learning (FL) is a promising privacy-preserving machine learning paradigm that allows data owners to collaboratively train models while keeping their data localized. Despite its potential, FL faces challenges related to the…

As deep neural networks (DNNs) are widely applied in the physical world, many researches are focusing on physical-world adversarial examples (PAEs), which introduce perturbations to inputs and cause the model's incorrect outputs. However,…

Personalized federated learning (PFL) addresses a critical challenge of collaboratively training customized models for clients with heterogeneous and scarce local data. Conventional federated learning, which relies on a single consensus…

Security has become a main concern for the smart grid to move from research and development to industry. The concept of security has usually referred to resistance to threats by an active or passive attacker. However, since smart meters…