No abstract

Graph Neural Networks (GNNs) are a class of deep learning-based methods for processing graph domain information. GNNs have recently become a widely used graph analysis method due to their superior ability to learn representations for complex graph data. However, due to privacy concerns and regulation restrictions, centralized GNNs can be difficult to apply to data-sensitive scenarios. Federated learning (FL) is an emerging technology developed for privacy-preserving settings when several parties need to train a shared global model collaboratively. Although many research works have applied FL to train GNNs (Federated GNNs), there is no research on their robustness to backdoor attacks.This paper bridges this gap by conducting two types of backdoor attacks in Federated GNNs: centralized backdoor attacks (CBA) and distributed backdoor attacks (DBA). CBA is conducted by embedding the same global trigger during training for every malicious party, while DBA is conducted by decomposing a global trigger into separate local triggers and embedding them into the training dataset of different malicious parties, respectively. Our experiments show that the DBA attack success rate is higher than CBA in almost all evaluated cases, while rarely, the DBA attack performance is close to CBA. For CBA, the attack success rate of all local triggers is similar to the global trigger even if the training set of the adversarial party is embedded with the global trigger. To further explore the properties of two backdoor attacks in Federated GNNs, we evaluate the attack performance for different trigger sizes, poisoning intensities, and trigger densities, with trigger density being the most influential.

Deep neural networks represent a powerful option for many realworld applications due to their ability to model even complex data relations. However, such neural networks can also be prohibitively expensive to train, making it common to either outsource the training process to third parties or use pretrained neural networks. Unfortunately, such practices make neural networks vulnerable to various attacks, where one attack is the backdoor attack. In such an attack, the third party training the model may maliciously inject hidden behaviors into the model. Still, if a particular input (called trigger) is fed into a neural network, the network will respond with a wrong result.In this work, we explore the option of backdoor attacks to automatic speech recognition systems where we inject inaudible triggers. By doing so, we make the backdoor attack challenging to detect for legitimate users, and thus, potentially more dangerous. We conduct experiments on two versions of datasets and three neural networks and explore the performance of our attack concerning the duration, position, and type of the trigger. Our results indicate that less than 1% of poisoned data is sufficient to deploy a backdoor attack and reach a 100% attack success rate. What is more, while the trigger is inaudible, making it without limitations with respect to the duration of the signal, we observed that even short, non-continuous triggers result in highly successful attacks. CCS CONCEPTS• Security and privacy → Systems security; • Computing methodologies → Speech recognition; Neural networks.

Since Administrative Science approach the various aspects of management in a multidimensional

Outsourced training and machine learning as a service have resulted in novel attack vectors like backdoor attacks. Such attacks embed a secret functionality in a neural network activated when the trigger is added to its input. In most works in the literature, the trigger is static, both in terms of location and pattern. The effectiveness of various detection mechanisms depends on this property. It was recently shown that countermeasures in image classification, like Neural Cleanse and ABS, could be bypassed with dynamic triggers that are effective regardless of their pattern and location. Still, such backdoors are demanding as they require a large percentage of poisoned training data. In this work, we are the first to show that dynamic backdoor attacks could happen due to a global average pooling layer without increasing the percentage of the poisoned training data. Nevertheless, our experiments in sound classification, text sentiment analysis, and image classification show this to be very difficult in practice.