Related papers: Defense Against Model Stealing Based on Account-Aw…
Membership inference attacks have emerged as a significant privacy concern in the training of deep learning models, where attackers can infer whether a data point was part of the training set based on the model's outputs. To address this…
Deep neural networks (DNNs) are powerful nonlinear architectures that are known to be robust to random perturbations of the input. However, these models are vulnerable to adversarial perturbations--small input changes crafted explicitly to…
The ability of the deep learning model to recognize when a sample falls outside its learned distribution is critical for safe and reliable deployment. Recent state-of-the-art out-of-distribution (OOD) detection methods leverage activation…
Anomaly detection is often considered a challenging field of machine learning due to the difficulty of obtaining anomalous samples for training and the need to obtain a sufficient amount of training data. In recent years, autoencoders have…
Deep neural networks (DNNs) are vulnerable to adversarial attack which is maliciously implemented by adding human-imperceptible perturbation to images and thus leads to incorrect prediction. Existing studies have proposed various methods to…
Anomaly detection is facing with emerging challenges in many important industry domains, such as cyber security and online recommendation and advertising. The recent trend in these areas calls for anomaly detection on time-evolving data…
Training a unified model is considered to be more suitable for practical industrial anomaly detection scenarios due to its generalization ability and storage efficiency. However, this multi-class setting, which exclusively uses normal data,…
The success of deep neural networks (DNNs) has promoted the widespread applications of person re-identification (ReID). However, ReID systems inherit the vulnerability of DNNs to malicious attacks of visually inconspicuous adversarial…
Automatic detection of anomalies such as weapons or threat objects in baggage security, or detecting impaired items in industrial production is an important computer vision task demanding high efficiency and accuracy. Most of the available…
Adversarial attack is commonly regarded as a huge threat to neural networks because of misleading behavior. This paper presents an opposite perspective: adversarial attacks can be harnessed to improve neural models if amended correctly.…
Generative models estimate the underlying distribution of a dataset to generate realistic samples according to that distribution. In this paper, we present the first membership inference attacks against generative models: given a data…
3D Anomaly Detection (AD) has shown great potential in detecting anomalies or defects of high-precision industrial products. However, existing methods are typically trained in a class-specific manner and also lack the capability of learning…
Deep Neural Networks (DNNs) are highly sensitive to imperceptible malicious perturbations, known as adversarial attacks. Following the discovery of this vulnerability in real-world imaging and vision applications, the associated safety…
Despite the great achievements of deep neural networks (DNNs), the vulnerability of state-of-the-art DNNs raises security concerns of DNNs in many application domains requiring high reliability.We propose the fault sneaking attack on DNNs,…
Adversarial attacks involve adding perturbations to the source image to cause misclassification by the target model, which demonstrates the potential of attacking face recognition models. Existing adversarial face image generation methods…
Out-of-distribution (OOD) detection has recently gained substantial attention due to the importance of identifying out-of-domain samples in reliability and safety. Although OOD detection methods have advanced by a great deal, they are still…
Despite numerous attempts to defend deep learning based image classifiers, they remain susceptible to the adversarial attacks. This paper proposes a technique to identify susceptible classes, those classes that are more easily subverted. To…
Anomaly detection-based spoof attack detection is a recent development in face Presentation Attack Detection (fPAD), where a spoof detector is learned using only non-attacked images of users. These detectors are of practical importance as…
Out-of-distribution (OOD) detection is essential for ensuring the robustness of machine learning models by identifying samples that deviate from the training distribution. While traditional OOD detection has primarily focused on…
Regression models, which are widely used from engineering applications to financial forecasting, are vulnerable to targeted malicious attacks such as training data poisoning, through which adversaries can manipulate their predictions.…