相关论文: Attention Masks Help Adversarial Attacks to Bypass…

Spiking neural networks (SNNs) have shown their competence in handling spatial-temporal event-based data with low energy consumption. Similar to conventional artificial neural networks (ANNs), SNNs are also vulnerable to gradient-based…

Neural networks are vulnerable to adversarial examples, which poses a threat to their application in security sensitive systems. We propose high-level representation guided denoiser (HGD) as a defense for image classification. Standard…

Training state-of-the-art (SOTA) deep learning models requires a large amount of data. The visual information present in the training data can be misused, which creates a huge privacy concern. One of the prominent solutions for this issue…

In this paper we propose to augment a modern neural-network architecture with an attention model inspired by human perception. Specifically, we adversarially train and analyze a neural model incorporating a human inspired, visual attention…

Diffusion models have demonstrated strong generative performance when using guidance methods such as classifier-free guidance (CFG), which enhance output quality by modifying the sampling trajectory. These methods typically improve a target…

Mask-based annotation of medical images, especially for 3D data, is a bottleneck in developing reliable machine learning models. Using minimal-labor user interactions (UIs) to guide the annotation is promising, but challenges remain on best…

Recent advances show that deep neural networks are not robust to deliberately crafted adversarial examples which many are generated by adding human imperceptible perturbation to clear input. Consider $l_2$ norms attacks, Project Gradient…

Advanced Persistent Threats (APT) pose a major cybersecurity challenge due to their stealth, persistence, and adaptability. Traditional machine learning detectors struggle with class imbalance, high dimensional features, and scarce real…

In the domain of cloud-based deep learning, the imperative for external computational resources coexists with acute privacy concerns, particularly identity leakage. To address this challenge, we introduce XNN and XNN-d, pioneering…

The convergence of artificial AI and XR technologies (AI XR) promises innovative applications across many domains. However, the sensitive nature of data (e.g., eye-tracking) used in these systems raises significant privacy concerns, as…

Manual visual inspection performed by certified inspectors is still the main form of road pothole detection. This process is, however, not only tedious, time-consuming and costly, but also dangerous for the inspectors. Furthermore, the road…

This work shows that it is possible to fool/attack recent state-of-the-art face detectors which are based on the single-stage networks. Successfully attacking face detectors could be a serious malware vulnerability when deploying a smart…

We present MS-GAGA (Metric-Selective Guided Adversarial Generation Attack), a two-stage framework for crafting transferable and visually imperceptible adversarial examples against deepfake detectors in black-box settings. In Stage 1, a…

Vision transformers (ViTs) have demonstrated impressive performance on a series of computer vision tasks, yet they still suffer from adversarial examples. % crafted in a similar fashion as CNNs. In this paper, we posit that adversarial…

Deep neural networks for classification are vulnerable to adversarial attacks, where small perturbations to input samples lead to incorrect predictions. This susceptibility, combined with the black-box nature of such networks, limits their…

Recently, transformer-based methods have dominated 3D instance segmentation, where mask attention is commonly involved. Specifically, object queries are guided by the initial instance masks in the first cross-attention, and then iteratively…

Recently, deep neural networks (DNNs) have made great progress on automated diagnosis with chest X-rays images. However, DNNs are vulnerable to adversarial examples, which may cause misdiagnoses to patients when applying the DNN based…

Existing approaches for unsupervised domain adaptive object detection perform feature alignment via adversarial training. While these methods achieve reasonable improvements in performance, they typically perform category-agnostic domain…

Accurate segmentation of glioma brain tumors is crucial for diagnosis and treatment planning. Deep learning techniques offer promising solutions, but optimal model architectures remain under investigation. We used the BraTS 2021 dataset,…

In recent years, the convolutional neural networks (CNNs) have received a lot of interest in the side-channel community. The previous work has shown that CNNs have the potential of breaking the cryptographic algorithm protected with masking…