Related papers: Everywhere Attack: Attacking Locally and Globally …
Quantized neural networks (QNNs) have received increasing attention in resource-constrained scenarios due to their exceptional generalizability. However, their robustness against realistic black-box adversarial attacks has not been…
The ability to transfer adversarial attacks from one model (the surrogate) to another model (the victim) has been an issue of concern within the machine learning (ML) community. The ability to successfully evade unseen models represents an…
Achieving transferability of targeted attacks is reputed to be remarkably difficult. Currently, state-of-the-art approaches are resource-intensive because they necessitate training model(s) for each target class with additional data. In our…
Malicious attackers can generate targeted adversarial examples by imposing tiny noises, forcing neural networks to produce specific incorrect outputs. With cross-model transferability, network models remain vulnerable even in black-box…
Neural networks are known to be vulnerable to carefully crafted adversarial examples, and these malicious samples often transfer, i.e., they maintain their effectiveness even against other models. With great efforts delved into the…
Deep learning models are known to be vulnerable to adversarial examples crafted by adding human-imperceptible perturbations on benign images. Many existing adversarial attack methods have achieved great white-box attack performance, but…
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 (AE) with good transferability enable practical black-box attacks on diverse target models, where insider knowledge about the target models is not required. Previous methods often generate AE with no or very limited…
Adversarial examples (AEs) for DNNs have been shown to be transferable: AEs that successfully fool white-box surrogate models can also deceive other black-box models with different architectures. Although a bunch of empirical studies have…
Deep neural networks have shown their vulnerability to adversarial attacks. In this paper, we focus on sparse adversarial attack based on the $\ell_0$ norm constraint, which can succeed by only modifying a few pixels of an image. Despite a…
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,…
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…
Deep neural networks are vulnerable to adversarial examples crafted by applying human-imperceptible perturbations on clean inputs. Although many attack methods can achieve high success rates in the white-box setting, they also exhibit weak…
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…
Multimodal pre-trained models (e.g., ImageBind), which align distinct data modalities into a shared embedding space, have shown remarkable success across downstream tasks. However, their increasing adoption raises serious security concerns,…
Adversarial attacks with improved transferability - the ability of an adversarial example crafted on a known model to also fool unknown models - have recently received much attention due to their practicality. Nevertheless, existing…
Previous works have extensively studied the transferability of adversarial samples in untargeted black-box scenarios. However, it still remains challenging to craft targeted adversarial examples with higher transferability than non-targeted…
The generation of transferable adversarial perturbations typically involves training a generator to maximize embedding separation between clean and adversarial images at a single mid-layer of a source model. In this work, we build on this…
State-of-the-art deep neural networks are known to be vulnerable to adversarial examples, formed by applying small but malicious perturbations to the original inputs. Moreover, the perturbations can \textit{transfer across models}:…
Adversarial examples have posed a severe threat to deep neural networks due to their transferable nature. Currently, various works have paid great efforts to enhance the cross-model transferability, which mostly assume the substitute model…