Related papers: Exploring Adversarial Attacks against Latent Diffu…

Intentionally crafted adversarial samples have effectively exploited weaknesses in deep neural networks. A standard method in adversarial robustness assumes a framework to defend against samples crafted by minimally perturbing a sample such…

In the field of Medical Imaging, extensive research has been dedicated to leveraging its potential in uncovering critical diagnostic features in patients. Artificial Intelligence (AI)-driven medical diagnosis relies on sophisticated machine…

Machine Learning (ML) and Deep Learning (DL) models have achieved state-of-the-art performance on multiple learning tasks, from vision to natural language modelling. With the growing adoption of ML and DL to many areas of computer science,…

Adversarial training is an effective method to boost model robustness to malicious, adversarial attacks. However, such improvement in model robustness often leads to a significant sacrifice of standard performance on clean images. In many…

Deep learning models are known to be vulnerable to adversarial examples. A practical adversarial attack should require as little as possible knowledge of attacked models. Current substitute attacks need pre-trained models to generate…

The transferability of adversarial examples across deep neural networks (DNNs) is the crux of many black-box attacks. Many prior efforts have been devoted to improving the transferability via increasing the diversity in inputs of some…

Deep neural networks obtain state-of-the-art performance on a series of tasks. However, they are easily fooled by adding a small adversarial perturbation to input. The perturbation is often human imperceptible on image data. We observe a…

Although deep-learning based video recognition models have achieved remarkable success, they are vulnerable to adversarial examples that are generated by adding human-imperceptible perturbations on clean video samples. As indicated in…

We introduce the Adversarial Confusion Attack, a new class of threats against multimodal large language models (MLLMs). Unlike jailbreaks or targeted misclassification, the goal is to induce systematic disruption that makes the model…

The integration of Large Language Models (LLMs) into healthcare applications offers promising advancements in medical diagnostics, treatment recommendations, and patient care. However, the susceptibility of LLMs to adversarial attacks poses…

To guarantee safe and robust deployment of large language models (LLMs) at scale, it is critical to accurately assess their adversarial robustness. Existing adversarial attacks typically target harmful responses in single-point greedy…

Recent advances in mechanistic interpretability suggest that intermediate attention layers encode token-level hypotheses that are iteratively refined toward the final output. In this work, we exploit this property to generate adversarial…

Deep neural network architectures are considered to be robust to random perturbations. Nevertheless, it was shown that they could be severely vulnerable to slight but carefully crafted perturbations of the input, termed as adversarial…

Adversarial attacks can mislead deep neural networks (DNNs) by adding imperceptible perturbations to benign examples. The attack transferability enables adversarial examples to attack black-box DNNs with unknown architectures or parameters,…

Adversarial examples for neural network image classifiers are known to be transferable: examples optimized to be misclassified by a source classifier are often misclassified as well by classifiers with different architectures. However,…

Recently, adversarial attacks for diffusion models as well as their fine-tuning process have been developed rapidly. To prevent the abuse of these attack algorithms from affecting the practical application of diffusion models, it is…

Adversarial examples add imperceptible alterations to inputs with the objective to induce misclassification in machine learning models. They have been demonstrated to pose significant challenges in domains like image classification, with…

We present a new method for black-box adversarial attack. Unlike previous methods that combined transfer-based and scored-based methods by using the gradient or initialization of a surrogate white-box model, this new method tries to learn a…

Transferability of adversarial examples is of critical importance to launch black-box adversarial attacks, where attackers are only allowed to access the output of the target model. However, under such a challenging but practical setting,…

Recent approaches employing imperceptible perturbations in input images have demonstrated promising potential to counter malicious manipulations in diffusion-based image editing systems. However, existing methods suffer from limited…