Related papers: BAARD: Blocking Adversarial Examples by Testing fo…

Benefiting from the rapid development of deep learning, 2D and 3D computer vision applications are deployed in many safe-critical systems, such as autopilot and identity authentication. However, deep learning models are not trustworthy…

Artificial intelligence is known as the most effective technological field for rapid developments shaping the future of the world. Even today, it is possible to see intense use of intelligence systems in all fields of the life. Although…

The identification of phases of matter is a challenging task, especially in quantum mechanics, where the complexity of the ground state appears to grow exponentially with the size of the system. We address this problem with state-of-the-art…

Detection of adversarial examples has been a hot topic in the last years due to its importance for safely deploying machine learning algorithms in critical applications. However, the detection methods are generally validated by assuming a…

As deep neural networks (DNNs) have become increasingly important and popular, the robustness of DNNs is the key to the safety of both the Internet and the physical world. Unfortunately, some recent studies show that adversarial examples,…

Tree ensembles are powerful models that are widely used. However, they are susceptible to adversarial examples, which are examples that purposely constructed to elicit a misprediction from the model. This can degrade performance and erode a…

Deep learning technology has made great achievements in the field of image. In order to defend against malware attacks, researchers have proposed many Windows malware detection models based on deep learning. However, deep learning models…

As Large Language Models quickly become ubiquitous, it becomes critical to understand their security vulnerabilities. Recent work shows that text optimizers can produce jailbreaking prompts that bypass moderation and alignment. Drawing from…

Adversarial machine learning is a fast growing research area, which considers the scenarios when machine learning systems may face potential adversarial attackers, who intentionally synthesize input data to make a well-trained model to make…

Malware is constantly adapting in order to avoid detection. Model based malware detectors, such as SVM and neural networks, are vulnerable to so-called adversarial examples which are modest changes to detectable malware that allows the…

Distribution shifts and adversarial examples are two major challenges for deploying machine learning models. While these challenges have been studied individually, their combination is an important topic that remains relatively…

Adversarial examples add imperceptible alterations to inputs with the objective to induce misclassification in machine learning models. They have been demonstrated to pose significant challenges in domains like image classification, with…

Advances in Machine Learning (ML) have led to its adoption as an integral component in many applications, including banking, medical diagnosis, and driverless cars. To further broaden the use of ML models, cloud-based services offered by…

Deep neural network (DNN) is a popular model implemented in many systems to handle complex tasks such as image classification, object recognition, natural language processing etc. Consequently DNN structural vulnerabilities become part of…

Deep neural networks (DNNs) are known to be vulnerable to adversarial examples which contain human-imperceptible perturbations. A series of defending methods, either proactive defence or reactive defence, have been proposed in the recent…

We present a mechanism for detecting adversarial examples based on data representations taken from the hidden layers of the target network. For this purpose, we train individual autoencoders at intermediate layers of the target network.…

Machine learning models have demonstrated vulnerability to adversarial attacks, more specifically misclassification of adversarial examples. In this paper, we propose a one-off and attack-agnostic Feature Manipulation (FM)-Defense to detect…

Face Presentation Attack Detection (PAD) has drawn increasing attentions to secure the face recognition systems that are widely used in many applications. Conventional face anti-spoofing methods have been proposed, assuming that testing is…

Recent studies show that models trained by continual learning can achieve the comparable performances as the standard supervised learning and the learning flexibility of continual learning models enables their wide applications in the real…

Privacy preserving has become increasingly critical with the emergence of social media. Unlearnable examples have been proposed to avoid leaking personal information on the Internet by degrading generalization abilities of deep learning…