Related papers: From Pixels to Trajectory: Universal Adversarial E…

The growing incorporation of artificial neural networks (NNs) into many fields, and especially into life-critical systems, is restrained by their vulnerability to adversarial examples (AEs). Some existing defense methods can increase NNs'…

Large pre-trained Vision-Language Models (VLMs) such as CLIP have demonstrated excellent zero-shot generalizability across various downstream tasks. However, recent studies have shown that the inference performance of CLIP can be greatly…

Rapid advances in Artificial Intelligence Generated Images (AIGI) have facilitated malicious use, such as forgery and misinformation. Therefore, numerous methods have been proposed to detect fake images. Although such detectors have been…

Adding perturbations via utilizing auxiliary gradient information or discarding existing details of the benign images are two common approaches for generating adversarial examples. Though visual imperceptibility is the desired property of…

We introduce the Temporal Contrastive Transformer (TCT), a representation learning framework designed to capture contextual temporal dynamics in sequences of financial transactions. The model is trained using a self-supervised contrastive…

Adversarial Examples (AEs) can deceive Deep Neural Networks (DNNs) and have received a lot of attention recently. However, majority of the research on AEs is in the digital domain and the adversarial patches are static, which is very…

In this paper, we study adversarial training on datasets that obey the long-tailed distribution, which is practical but rarely explored in previous works. Compared with conventional adversarial training on balanced datasets, this process…

Trajectory data, capturing human actions and environmental states across various modalities, holds significant potential for enhancing AI agent capabilities, particularly in GUI environments. However, how to model the representation of…

The utilization of large foundational models has a dilemma: while fine-tuning downstream tasks from them holds promise for making use of the well-generalized knowledge in practical applications, their open accessibility also poses threats…

Electrical impedance tomography (EIT) has been successfully applied to several important application domains such as medicine, geophysics and industrial imaging. EIT offers a high temporal resolution, which allows to track the location of a…

Visual tracking is adopted to extensive unmanned aerial vehicle (UAV)-related applications, which leads to a highly demanding requirement on the robustness of UAV trackers. However, adding imperceptible perturbations can easily fool the…

Pedestrian Attribute Recognition (PAR) is an indispensable task in human-centered research and has made great progress in recent years with the development of deep neural networks. However, the potential vulnerability and anti-interference…

The vulnerability of deep neural networks to adversarial examples has drawn tremendous attention from the community. Three approaches, optimizing standard objective functions, exploiting attention maps, and smoothing decision surfaces, are…

Physical adversarial attacks threaten to fool object detection systems, but reproducible research on the real-world effectiveness of physical patches and how to defend against them requires a publicly available benchmark dataset. We present…

Taking into account information across the temporal domain helps to improve environment perception in autonomous driving. However, it has not been studied so far whether temporally fused neural networks are vulnerable to deliberately…

Adversarial examples' (AE) transferability refers to the phenomenon that AEs crafted with one surrogate model can also fool other models. Notwithstanding remarkable progress in untargeted transferability, its targeted counterpart remains…

Image attribution -- matching an image back to a trusted source -- is an emerging tool in the fight against online misinformation. Deep visual fingerprinting models have recently been explored for this purpose. However, they are not robust…

An ever-growing body of work has demonstrated the rich information content available in eye movements for user modelling, e.g. for predicting users' activities, cognitive processes, or even personality traits. We show that state-of-the-art…

Learning to compute, the ability to model the functional behavior of a circuit graph, is a fundamental challenge for graph representation learning. Yet, the dominant paradigm is architecturally mismatched for this task. This flawed…

Sparse representation has been widely studied in visual tracking, which has shown promising tracking performance. Despite a lot of progress, the visual tracking problem is still a challenging task due to appearance variations over time. In…