相关论文: MiniFool -- Physics-Constraint-Aware Minimizer-Bas…

State-of-the-art machine learning models are vulnerable to data poisoning attacks whose purpose is to undermine the integrity of the model. However, the current literature on data poisoning attacks is mainly focused on ad hoc techniques…

Deep neural networks (DNNs) have transformed several artificial intelligence research areas including computer vision, speech recognition, and natural language processing. However, recent studies demonstrated that DNNs are vulnerable to…

Deep neural networks are vulnerable to adversarial examples, i.e., carefully-perturbed inputs aimed to mislead classification. This work proposes a detection method based on combining non-linear dimensionality reduction and density…

Deep neural network architectures are considered to be robust to random perturbations. Nevertheless, it was shown that they could be severely vulnerable to slight but carefully crafted perturbations of the input, termed as adversarial…

We introduce a novel machine unlearning framework founded upon the established principles of the min-max optimization paradigm. We capitalize on the capabilities of strong Membership Inference Attacks (MIA) to facilitate the unlearning of…

Deep Learning has empowered us to train neural networks for complex data with high performance. However, with the growing research, several vulnerabilities in neural networks have been exposed. A particular branch of research, Adversarial…

Despite substantial advances in network architecture performance, the susceptibility of adversarial attacks makes deep learning challenging to implement in safety-critical applications. This paper proposes a data-centric approach to…

Adversarial attacks for image classification are small perturbations to images that are designed to cause misclassification by a model. Adversarial attacks formally correspond to an optimization problem: find a minimum norm image…

Deep neural networks (DNN) have been shown to be useful in a wide range of applications. However, they are also known to be vulnerable to adversarial samples. By transforming a normal sample with some carefully crafted human imperceptible…

We propose a novel approach towards adversarial attacks on neural networks (NN), focusing on tampering the data used for training instead of generating attacks on trained models. Our network-agnostic method creates a backdoor during…

Nearest prototype classifiers (NPCs) assign to each input point the label of the nearest prototype with respect to a chosen distance metric. A direct advantage of NPCs is that the decisions are interpretable. Previous work could provide…

We present an algorithm for computing class-specific universal adversarial perturbations for deep neural networks. Such perturbations can induce misclassification in a large fraction of images of a specific class. Unlike previous methods…

Despite the efficiency and scalability of machine learning systems, recent studies have demonstrated that many classification methods, especially deep neural networks (DNNs), are vulnerable to adversarial examples; i.e., examples that are…

The ability of machine learning (ML) classification models to resist small, targeted input perturbations -- known as adversarial attacks -- is a key measure of their safety and reliability. We show that floating-point non-associativity…

Autonomous flying robots, e.g. multirotors, often rely on a neural network that makes predictions based on a camera image. These deep learning (DL) models can compute surprising results if applied to input images outside the training…

Thousands of person-years have been invested in searches for New Physics (NP), the majority of them motivated by theoretical considerations. Yet, no evidence of beyond the Standard Model (BSM) physics has been found. This suggests that…

Neural network classifiers are vulnerable to misclassification of adversarial samples, for which the current best defense trains classifiers with adversarial samples. However, adversarial samples are not optimal for steering attack…

The paper develops a new adversarial attack against deep neural networks (DNN), based on applying bio-inspired design to moving physical objects. To the best of our knowledge, this is the first work to introduce physical attacks with a…

Video classification systems are vulnerable to adversarial attacks, which can create severe security problems in video verification. Current black-box attacks need a large number of queries to succeed, resulting in high computational…

Deep reinforcement learning algorithms that estimate state and state-action value functions have been shown to be effective in a variety of challenging domains, including learning control strategies from raw image pixels. However,…