相关论文: Why Do Adversarial Attacks Transfer? Explaining Tr…

Transfer learning is a powerful technique for knowledge-sharing between different tasks. Recent work has found that the representations of models with certain invariances, such as to adversarial input perturbations, achieve higher…

An established way to improve the transferability of black-box evasion attacks is to craft the adversarial examples on an ensemble-based surrogate to increase diversity. We argue that transferability is fundamentally related to uncertainty.…

Advanced text-to-image diffusion models raise safety concerns regarding identity privacy violation, copyright infringement, and Not Safe For Work content generation. Towards this, unlearning methods have been developed to erase these…

espite being widely used in network intrusion detection systems (NIDSs), machine learning (ML) has proven to be highly vulnerable to adversarial attacks. White-box and black-box adversarial attacks of NIDS have been explored in several…

Deep neural networks are vulnerable to adversarial examples, which can fool deep models by adding subtle perturbations. Although existing attacks have achieved promising results, it still leaves a long way to go for generating transferable…

We present a data poisoning attack -- Phantom Transfer -- with the property that, even if you know precisely how the poison was placed into an otherwise benign dataset, you cannot filter it out. We achieve this by modifying subliminal…

In the past decades, the rise of artificial intelligence has given us the capabilities to solve the most challenging problems in our day-to-day lives, such as cancer prediction and autonomous navigation. However, these applications might…

Adversarial Transferability is an intriguing property - adversarial perturbation crafted against one model is also effective against another model, while these models are from different model families or training processes. To better…

There has been emerging interest to use transductive learning for adversarial robustness (Goldwasser et al., NeurIPS 2020; Wu et al., ICML 2020). Compared to traditional "test-time" defenses, these defense mechanisms "dynamically retrain"…

The financial industry relies on deep learning models for making important decisions. This adoption brings new danger, as deep black-box models are known to be vulnerable to adversarial attacks. In computer vision, one can shape the output…

Although many methods have been proposed to enhance the transferability of adversarial perturbations, these methods are designed in a heuristic manner, and the essential mechanism for improving adversarial transferability is still unclear.…

The adversarial machine learning literature is largely partitioned into evasion attacks on testing data and poisoning attacks on training data. In this work, we show that adversarial examples, originally intended for attacking pre-trained…

Adversarial training is an effective defense method to protect classification models against adversarial attacks. However, one limitation of this approach is that it can require orders of magnitude additional training time due to high cost…

Deep Neural Networks (DNNs) are known to be vulnerable to adversarial examples. Further, these adversarial examples are found to be transferable from the source network in which they are crafted to a black-box target network. As the trend…

Adversarial attacks are widely used to evaluate model robustness, and in black-box scenarios, the transferability of these attacks becomes crucial. Existing generator-based attacks have excellent generalization and transferability due to…

Recent research has found that many families of machine learning models are vulnerable to adversarial examples: inputs that are specifically designed to cause the target model to produce erroneous outputs. In this survey, we focus on…

Machine learning is susceptible to poisoning attacks, in which an attacker controls a small fraction of the training data and chooses that data with the goal of inducing some behavior unintended by the model developer in the trained model.…

Deep neural networks (DNNs) are highly susceptible to adversarial examples--subtle perturbations applied to inputs that are often imperceptible to humans yet lead to incorrect model predictions. In black-box scenarios, however, existing…

An adversarial deep learning approach is presented to launch over-the-air spectrum poisoning attacks. A transmitter applies deep learning on its spectrum sensing results to predict idle time slots for data transmission. In the meantime, an…

Growing at a fast pace, modern autonomous systems will soon be deployed at scale, opening up the possibility for cooperative multi-agent systems. Sharing information and distributing workloads allow autonomous agents to better perform tasks…