Related papers: Crossfire: An Elastic Defense Framework for Graph …
Recent studies have shown that graph neural networks (GNNs) are vulnerable to adversarial attacks, posing significant challenges to their deployment in safety-critical scenarios. This vulnerability has spurred a growing focus on designing…
Deep neural networks (DNNs) are state-of-the-art algorithms for multiple applications, spanning from image classification to speech recognition. While providing excellent accuracy, they often have enormous compute and memory requirements.…
Mission-critical embedded software is critical to our society's infrastructure but can be subject to new security vulnerabilities as technology advances. When security issues arise, Reverse Engineers (REs) use Software Reverse Engineering…
Drone imagery is increasingly used in automated inspection for infrastructure surface defects, especially in hazardous or unreachable environments. In machine vision, the key to crack detection rests with robust and accurate algorithms for…
Graph Neural Networks (GNNs) is a promising approach for applications with nonEuclidean data. However, training GNNs on large scale graphs with hundreds of millions nodes is both resource and time consuming. Different from DNNs, GNNs…
Deep neural network (DNN) predictions have been shown to be vulnerable to carefully crafted adversarial perturbations. Specifically, image-agnostic (universal adversarial) perturbations added to any image can fool a target network into…
In this paper, we present Zero-data Based Repeated bit flip Attack (ZeBRA) that precisely destroys deep neural networks (DNNs) by synthesizing its own attack datasets. Many prior works on adversarial weight attack require not only the…
Cyberterrorism poses a formidable threat to digital infrastructures, with increasing reliance on encrypted, decentralized platforms that obscure threat actor activity. To address the challenge of analyzing such adversarial networks while…
Federated graph learning (FedGL) is an emerging federated learning (FL) framework that extends FL to learn graph data from diverse sources. FL for non-graph data has shown to be vulnerable to backdoor attacks, which inject a shared backdoor…
Graph Neural Networks (GNNs) have become widely used in the field of graph mining. However, these networks are vulnerable to structural perturbations. While many research efforts have focused on analyzing vulnerability through poisoning…
We present the Graph Forward-Forward (GFF) algorithm, an extension of the Forward-Forward procedure to graphs, able to handle features distributed over a graph's nodes. This allows training graph neural networks with forward passes only,…
Adversarial attacks on Graph Neural Networks (GNNs) reveal their security vulnerabilities, limiting their adoption in safety-critical applications. However, existing attack strategies rely on the knowledge of either the GNN model being used…
Counterfactual explanations offer an intuitive way to interpret graph neural networks (GNNs) by identifying minimal changes that alter a model's prediction, thereby answering "what must differ for a different outcome?". In this work, we…
Graph Neural Networks (GNNs) are highly vulnerable to adversarial attacks, which can greatly degrade their performance. Existing graph purification methods attempt to address this issue by filtering attacked graphs. However, they struggle…
In this paper, we study the adversarial attack and defence problem in deep learning from the perspective of Fourier analysis. We first explicitly compute the Fourier transform of deep ReLU neural networks and show that there exist decaying…
This paper presents a DNN bottleneck reinforcement scheme to alleviate the vulnerability of Deep Neural Networks (DNN) against adversarial attacks. Typical DNN classifiers encode the input image into a compressed latent representation more…
Model quantization is widely used to compress and accelerate deep neural networks. However, recent studies have revealed the feasibility of weaponizing model quantization via implanting quantization-conditioned backdoors (QCBs). These…
Federated Graph Learning (FedGL) is vulnerable to malicious attacks, yet developing a truly effective and stealthy attack method remains a significant challenge. Existing attack methods suffer from low attack success rates, high…
Graph Neural Networks(GNNs) are vulnerable to backdoor attacks, where adversaries implant malicious triggers to manipulate model predictions. Existing trigger generators are often simplistic in structure and overly reliant on specific…
Deep neural networks are not resilient to parameter corruptions: even a single-bitwise error in their parameters in memory can cause an accuracy drop of over 10%, and in the worst cases, up to 99%. This susceptibility poses great challenges…