Related papers: Adversarial Examples Make Strong Poisons

When data is publicly released for human consumption, it is unclear how to prevent its unauthorized usage for machine learning purposes. Successful model training may be preventable with carefully designed dataset modifications, and we…

Machine learning systems based on deep neural networks, being able to produce state-of-the-art results on various perception tasks, have gained mainstream adoption in many applications. However, they are shown to be vulnerable to…

Data poisoning attacks aim to manipulate the model produced by a learning algorithm by adversarially modifying the training set. We consider differential privacy as a defensive measure against this type of attack. We show that such learners…

This paper considers attacks against machine learning algorithms used in remote sensing applications, a domain that presents a suite of challenges that are not fully addressed by current research focused on natural image data such as…

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…

Adversarial examples are input examples that are specifically crafted to deceive machine learning classifiers. State-of-the-art adversarial example detection methods characterize an input example as adversarial either by quantifying the…

Although ImageNet was initially proposed as a dataset for performance benchmarking in the domain of computer vision, it also enabled a variety of other research efforts. Adversarial machine learning is one such research effort, employing…

Machine learning classifiers are known to be vulnerable to inputs maliciously constructed by adversaries to force misclassification. Such adversarial examples have been extensively studied in the context of computer vision applications. In…

This paper examines the robustness of deployed few-shot meta-learning systems when they are fed an imperceptibly perturbed few-shot dataset. We attack amortized meta-learners, which allows us to craft colluding sets of inputs that are…

As the internet continues to be populated with new devices and emerging technologies, the attack surface grows exponentially. Technology is shifting towards a profit-driven Internet of Things market where security is an afterthought.…

Traditional adversarial attacks rely upon the perturbations generated by gradients from the network which are generally safeguarded by gradient guided search to provide an adversarial counterpart to the network. In this paper, we propose a…

Deep neural networks are vulnerable to backdoor attacks, a type of adversarial attack that poisons the training data to manipulate the behavior of models trained on such data. Clean-label attacks are a more stealthy form of backdoor attacks…

Adversarial examples are maliciously tweaked images that can easily fool machine learning techniques, such as neural networks, but they are normally not visually distinguishable for human beings. One of the main approaches to solve this…

Machine learning researchers have long noticed the phenomenon that the model training process will be more effective and efficient when the training samples are densely sampled around the underlying decision boundary. While this observation…

Adversarial examples are commonly viewed as a threat to ConvNets. Here we present an opposite perspective: adversarial examples can be used to improve image recognition models if harnessed in the right manner. We propose AdvProp, an…

Almost all adversarial attacks are formulated to add an imperceptible perturbation to an image in order to fool a model. Here, we consider the opposite which is adversarial examples that can fool a human but not a model. A large enough and…

Modern image classification systems are often built on deep neural networks, which suffer from adversarial examples--images with deliberately crafted, imperceptible noise to mislead the network's classification. To defend against…

It is well-known that deep learning models are vulnerable to small input perturbations. Such perturbed instances are called adversarial examples. Adversarial examples are commonly crafted to fool a model either at training time (poisoning)…

Adversarial examples are inputs to machine learning models designed by an adversary to cause an incorrect output. So far, adversarial examples have been studied most extensively in the image domain. In this domain, adversarial examples can…

Targeted data poisoning attacks manipulate model predictions on specific test samples by injecting malicious data into training. Yet existing evaluations report average attack success rates over randomly selected targets, obscuring true…