Related papers: Improving Homograph Attack Classification
The Structural Similarity Index (SSIM) is generally considered to be a milestone in the recent history of Image Quality Assessment (IQA). Alas, SSIM's accepted development from the product of three heuristic factors continues to obscure…
We investigate if the random feature selection approach proposed in [1] to improve the robustness of forensic detectors to targeted attacks, can be extended to detectors based on deep learning features. In particular, we study the…
As online fraudsters invest more resources, including purchasing large pools of fake user accounts and dedicated IPs, fraudulent attacks become less obvious and their detection becomes increasingly challenging. Existing approaches such as…
Weakly supervised object localization (WSOL) is a challenging problem which aims to localize objects with only image-level labels. Due to the lack of ground truth bounding boxes, class labels are mainly employed to train the model. This…
Recent studies show that Graph Neural Networks(GNNs) are vulnerable and easily fooled by small perturbations, which has raised considerable concerns for adapting GNNs in various safety-critical applications. In this work, we focus on the…
Backdoor attack injects malicious behavior to models such that inputs embedded with triggers are misclassified to a target label desired by the attacker. However, natural features may behave like triggers, causing misclassification once…
Topological correctness plays a critical role in many image segmentation tasks, yet most networks are trained using pixel-wise loss functions, such as Dice, neglecting topological accuracy. Existing topology-aware methods often lack robust…
Benchmark datasets that measure camera pose accuracy have driven progress in visual re-localisation research. To obtain poses for thousands of images, it is common to use a reference algorithm to generate pseudo ground truth. Popular…
Text-attributed graph (TAG) is an important type of graph structured data with text descriptions for each node. Few- and zero-shot node classification on TAGs have many applications in fields such as academia and social networks. However,…
Image-level weakly-supervised semantic segmentation (WSSS) reduces the usually vast data annotation cost by surrogate segmentation masks during training. The typical approach involves training an image classification network using global…
This paper rethinks image histogram matching (HM) and proposes a differentiable and parametric HM preprocessing for a downstream classifier. Convolutional neural networks have demonstrated remarkable achievements in classification tasks.…
Homophily, the tendency of nodes from the same class to connect, is a fundamental property of real-world graphs, underpinning structural and semantic patterns in domains such as citation networks and social networks. Existing methods…
Improving the performance on an imbalanced training set is one of the main challenges in nowadays Machine Learning. One way to augment and thus re-balance the image dataset is through existing deep generative models, like class-conditional…
Modifying characters of a piece of text to their visual similar ones often ap-pear in spam in order to fool inspection systems and other conditions, which we regard as a kind of adversarial attack to neural models. We pro-pose a way of…
A key topic in classification is the accuracy loss produced when the data distribution in the training (source) domain differs from that in the testing (target) domain. This is being recognized as a very relevant problem for many computer…
Deep Learning based AI systems have shown great promise in various domains such as vision, audio, autonomous systems (vehicles, drones), etc. Recent research on neural networks has shown the susceptibility of deep networks to adversarial…
Medical images like CT and MRI provide detailed information about the internal structure of the body, and identifying key anatomical structures from these images plays a crucial role in clinical workflows. Current methods treat it as a…
The Simultaneous Localization and Mapping (SLAM) problem addresses the possibility of a robot to localize itself in an unknown environment and simultaneously build a consistent map of this environment. Recently, cameras have been…
The currently leading artificial neural network models of the visual ventral stream - which are derived from a combination of performance optimization and robustification methods - have demonstrated a remarkable degree of behavioral…
Recent work has shown that additive threat models, which only permit the addition of bounded noise to the pixels of an image, are insufficient for fully capturing the space of imperceivable adversarial examples. For example, small rotations…