Related papers: Towards Highly Transferable Vision-Language Attack…

Continual learning (CL) aims to equip models with the ability to learn from a stream of tasks without forgetting previous knowledge. With the progress of vision-language models like Contrastive Language-Image Pre-training (CLIP), their…

The transferability of adversarial examples is a crucial aspect of evaluating the robustness of deep learning systems, particularly in black-box scenarios. Although several methods have been proposed to enhance cross-model transferability,…

Adversarial attacks pose a significant threat to deep learning models, particularly in safety-critical applications like healthcare and autonomous driving. Recently, patch based attacks have demonstrated effectiveness in real-time inference…

Recent studies have revealed the vulnerability of pre-trained language models to adversarial attacks. Existing adversarial defense techniques attempt to reconstruct adversarial examples within feature or text spaces. However, these methods…

Deep learning models, while achieving state-of-the-art performance on many tasks, are susceptible to adversarial attacks that exploit inherent vulnerabilities in their architectures. Adversarial attacks manipulate the input data with…

Visual Question Answering (VQA) has achieved great success thanks to the fast development of deep neural networks (DNN). On the other hand, the data augmentation, as one of the major tricks for DNN, has been widely used in many computer…

Matching information across image and text modalities is a fundamental challenge for many applications that involve both vision and natural language processing. The objective is to find efficient similarity metrics to compare the similarity…

Transferable attacks generate adversarial examples on surrogate models to fool unknown victim models, posing real-world threats and growing research interest. Despite focusing on flat losses for transferable adversarial examples, recent…

Visual language modeling for automated driving is emerging as a promising research direction with substantial improvements in multimodal reasoning capabilities. Despite its advanced reasoning abilities, VLM-AD remains vulnerable to serious…

The majority of methods for crafting adversarial attacks have focused on scenes with a single dominant object (e.g., images from ImageNet). On the other hand, natural scenes include multiple dominant objects that are semantically related.…

We focus on Unsupervised Domain Adaptation (UDA) for the task of semantic segmentation. Recently, adversarial alignment has been widely adopted to match the marginal distribution of feature representations across two domains globally.…

Domain adaptive semantic segmentation refers to making predictions on a certain target domain with only annotations of a specific source domain. Current state-of-the-art works suggest that performing category alignment can alleviate domain…

State-of-the-art deep neural networks have proven to be highly powerful in a broad range of tasks, including semantic image segmentation. However, these networks are vulnerable against adversarial attacks, i.e., non-perceptible…

Transferable adversarial attack is always in the spotlight since deep learning models have been demonstrated to be vulnerable to adversarial samples. However, existing physical attack methods do not pay enough attention on transferability…

Vision-language models (VLMs) are increasingly used in autonomous driving because they combine visual perception with language-based reasoning, supporting more interpretable decision-making, yet their robustness to physical adversarial…

This paper investigates the robustness of vision-language models against adversarial visual perturbations and introduces a novel ``double visual defense" to enhance this robustness. Unlike previous approaches that resort to lightweight…

Pre-trained vision-language (VL) models are highly vulnerable to adversarial attacks. However, existing defense methods primarily focus on image classification, overlooking two key aspects of VL tasks: multimodal attacks, where both image…

An adversarial attack paradigm explores various scenarios for the vulnerability of deep learning models: minor changes of the input can force a model failure. Most of the state of the art frameworks focus on adversarial attacks for images…

The robustness of deep learning models against adversarial attacks remains a pivotal concern. This study presents, for the first time, an exhaustive review of the transferability aspect of adversarial attacks. It systematically categorizes…

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…