相关论文: Adversarial Attacks to Multi-Modal Models

The majority of adversarial machine learning research focuses on additive attacks, which add adversarial perturbation to input data. On the other hand, unlike image recognition problems, only a handful of attack approaches have been…

Recent studies have shown that adversarial examples hand-crafted on one white-box model can be used to attack other black-box models. Such cross-model transferability makes it feasible to perform black-box attacks, which has raised security…

Adversarial transferability enables black-box attacks on unknown victim deep neural networks (DNNs), rendering attacks viable in real-world scenarios. Current transferable attacks create adversarial perturbation over the entire image,…

Modeling various aspects that make a music piece unique is a challenging task, requiring the combination of multiple sources of information. Deep learning is commonly used to obtain representations using various sources of information, such…

Deep learning models are vulnerable to various adversarial manipulations of their training data, parameters, and input sample. In particular, an adversary can modify the training data and model parameters to embed backdoors into the model,…

Though CNNs have achieved the state-of-the-art performance on various vision tasks, they are vulnerable to adversarial examples --- crafted by adding human-imperceptible perturbations to clean images. However, most of the existing…

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,…

A significant amount of work has been done on adversarial attacks that inject imperceptible noise to images to deteriorate the image classification performance of deep models. However, most of the existing studies consider attacks in the…

Large pre-trained models have achieved notable success across a range of downstream tasks. However, recent research shows that a type of adversarial attack ($\textit{i.e.,}$ backdoor attack) can manipulate the behavior of machine learning…

The convergence of cross-modal adversarial learning and physics-driven methods represents a cutting-edge direction for tackling challenges in complex multi-modal tasks and scientific computing. This review focuses on systematically…

An adversarial example is a modified input image designed to cause a Machine Learning (ML) model to make a mistake; these perturbations are often invisible or subtle to human observers and highlight vulnerabilities in a model's ability to…

Deep neural networks for image classification are well-known to be vulnerable to adversarial attacks. One such attack that has garnered recent attention is the adversarial backdoor attack, which has demonstrated the capability to perform…

AI systems can take harmful actions and are highly vulnerable to adversarial attacks. We present an approach, inspired by recent advances in representation engineering, that interrupts the models as they respond with harmful outputs with…

Multimodal large language models (MLLMs) remain vulnerable to transferable adversarial examples. While existing methods typically achieve targeted attacks by aligning global features-such as CLIP's [CLS] token-between adversarial and target…

We introduce new jailbreak attacks on vision language models (VLMs), which use aligned LLMs and are resilient to text-only jailbreak attacks. Specifically, we develop cross-modality attacks on alignment where we pair adversarial images…

We investigate the problem of reliable communication in the presence of active adversaries that can tamper with the transmitted data. We consider a legitimate transmitter-receiver pair connected over multiple communication paths (routes).…

Deep models have shown their vulnerability when processing adversarial samples. As for the black-box attack, without access to the architecture and weights of the attacked model, training a substitute model for adversarial attacks has…

We consider a wireless communication system that consists of a transmitter, a receiver, and an adversary. The transmitter transmits signals with different modulation types, while the receiver classifies its received signals to modulation…

As object detection becomes integral to many safety-critical applications, understanding its vulnerabilities is essential. Backdoor attacks, in particular, pose a serious threat by implanting hidden triggers in victim models, which…

As object detection becomes integral to many safety-critical applications, understanding its vulnerabilities is essential. Backdoor attacks, in particular, pose a serious threat by implanting hidden triggers in victim models, which…