Related papers: Image Shortcut Squeezing: Countering Perturbative …

Photoacoustic computed tomography (PACT) is an emerging computed imaging modality that exploits optical contrast and ultrasonic detection principles to form images of the absorbed optical energy density within tissue. When the imaging…

It is well known that adversarial attacks can fool deep neural networks with imperceptible perturbations. Although adversarial training significantly improves model robustness, failure cases of defense still broadly exist. In this work, we…

Deep neural network image classifiers are reported to be susceptible to adversarial evasion attacks, which use carefully crafted images created to mislead a classifier. Recently, various kinds of adversarial attack methods have been…

Channel pruning is formulated as a neural architecture search (NAS) problem recently. However, existing NAS-based methods are challenged by huge computational cost and inflexibility of applications. How to deal with multiple sparsity…

Black box attacks, where adversaries have limited knowledge of the target model, pose a significant threat to machine learning systems. Adversarial examples generated with a substitute model often suffer from limited transferability to the…

Ising machines (IM) are physics-inspired alternatives to von Neumann architectures for solving hard optimization tasks. By mapping binary variables to coupled Ising spins, IMs can naturally solve unconstrained combinatorial optimization…

Machine learning interatomic potentials (MLIPs) balance high accuracy and lower costs compared to density functional theory calculations, but their performance often depends on the size and diversity of training datasets. Large datasets…

Significance: Compressed sensing (CS) uses special measurement designs combined with powerful mathematical algorithms to reduce the amount of data to be collected while maintaining image quality. This is relevant to almost any imaging…

Advanced Persistent Threats (APTs) represent a sophisticated and persistent cy-bersecurity challenge, characterized by stealthy, multi-phase, and targeted attacks aimed at compromising information systems over an extended period.…

Self-supervised pre-training has drawn increasing attention in recent years due to its superior performance on numerous downstream tasks after fine-tuning. However, it is well-known that deep learning models lack the robustness to…

Text-to-image diffusion models have been widely adopted in real-world applications due to their ability to generate realistic images from textual descriptions. However, recent studies have shown that these methods are vulnerable to backdoor…

Modern large language models (LLMs) exhibit critical vulnerabilities to poison pill attacks: localized data poisoning that alters specific factual knowledge while preserving overall model utility. We systematically demonstrate these attacks…

Universal adversarial perturbations (UAPs), a.k.a. input-agnostic perturbations, has been proved to exist and be able to fool cutting-edge deep learning models on most of the data samples. Existing UAP methods mainly focus on attacking…

While adversarial perturbation of images to attack deep image classification models pose serious security concerns in practice, this paper suggests a novel paradigm where the concept of image perturbation can benefit classification…

Despite demonstrating superior rate-distortion (RD) performance, learning-based image compression (LIC) algorithms have been found to be vulnerable to malicious perturbations in recent studies. However, the adversarial attacks considered in…

While continuous diffusion models have achieved remarkable success, discrete diffusion offers a unified framework for jointly modeling text and images. Beyond unification, discrete diffusion provides faster inference, finer control, and…

Deep neural networks (DNNs) have been shown to be vulnerable to adversarial examples, which can produce erroneous predictions by injecting imperceptible perturbations. In this work, we study the transferability of adversarial examples,…

Transcranial ultrasound imaging is currently limited by attenuation and aberration induced by the skull. First used in contrast-enhanced ultrasound (CEUS), highly echoic microbubbles allowed for the development of novel imaging modalities…

In a poisoning attack, an adversary with control over a small fraction of the training data attempts to select that data in a way that induces a corrupted model that misbehaves in favor of the adversary. We consider poisoning attacks…

Input-to-State Stability (ISS) is fundamental in mathematically quantifying how stability degrades in the presence of bounded disturbances. If a system is ISS, its trajectories will remain bounded, and will converge to a neighborhood of an…