Related papers: ELDA: Towards Efficient and Lightweight Detection …

Targeted clean-label data poisoning is a type of adversarial attack on machine learning systems in which an adversary injects a few correctly-labeled, minimally-perturbed samples into the training data, causing a model to misclassify a…

Recent studies have shown convolution neural networks (CNNs) for image recognition are vulnerable to evasion attacks with carefully manipulated adversarial examples. Previous work primarily focused on how to generate adversarial examples…

In certain blockchain systems, light nodes are clients that download only a small portion of the block. Light nodes are vulnerable to data availability (DA) attacks where a malicious node hides an invalid portion of the block from the light…

Deep Neural Networks (DNNs) have been shown to be vulnerable to adversarial examples. While numerous successful adversarial attacks have been proposed, defenses against these attacks remain relatively understudied. Existing defense…

Network attack is a significant security issue for modern society. From small mobile devices to large cloud platforms, almost all computing products, used in our daily life, are networked and potentially under the threat of network…

Prior works on physical adversarial camouflage against vehicle detectors mainly focus on the effectiveness and robustness of the attack. The current most successful methods optimize 3D vehicle texture at a pixel level. However, this results…

Model stealing attacks have become a serious concern for deep learning models, where an attacker can steal a trained model by querying its black-box API. This can lead to intellectual property theft and other security and privacy risks. The…

Distributed Denial of Service (DDoS) attacks are one of the most harmful threats in today's Internet, disrupting the availability of essential services. The challenge of DDoS detection is the combination of attack approaches coupled with…

The threats of caching poisoning attacks largely stimulate the deployment of DNSSEC. Being a strong but demanding cryptographical defense, DNSSEC has its universal adoption predicted to go through a lengthy transition. Thus the DNSSEC…

Large Language Models (LLMs), such as GPT and LLaMA, introduce unique memory access characteristics during inference due to frequent token sequence lookups and embedding vector retrievals. These workloads generate highly irregular and…

Network coding based peer-to-peer streaming represents an effective solution to aggregate user capacities and to increase system throughput in live multimedia streaming. Nonetheless, such systems are vulnerable to pollution attacks where a…

Following the recent adoption of deep neural networks (DNN) accross a wide range of applications, adversarial attacks against these models have proven to be an indisputable threat. Adversarial samples are crafted with a deliberate intention…

Convolutional neural networks (CNN) define the state-of-the-art solution on many perceptual tasks. However, current CNN approaches largely remain vulnerable against adversarial perturbations of the input that have been crafted specifically…

In this work we investigate Named Data Networking's (NDN's) architectural properties and features, such as content caching and intelligent packet forwarding, in the context of a Content Delivery Network (CDN) workflows. More specifically,…

False Data Injection Attacks (FDIAs) pose a significant threat to smart grid infrastructures, particularly Home Area Networks (HANs), where real-time monitoring and control are highly adopted. Owing to the comparatively less stringent…

Peer-assisted content distribution networks(CDNs) have emerged to improve performance and reduce deployment costs of traditional, infrastructure-based content delivery networks. This is done by employing peer-to-peer data transfers to…

Information Centric Networking (ICN) is a new network architecture (Internet) that focuses on content rather than the end-hosts. Named Data Networking (NDN) is a specific implementation of ICN, which relies on the use of named data and a…

We propose a Universal Defence against backdoor attacks based on Clustering and Centroids Analysis (CCA-UD). The goal of the defence is to reveal whether a Deep Neural Network model is subject to a backdoor attack by inspecting the training…

Protecting cloud applications is critical in an era where security threats are increasingly sophisticated and persistent. Continuous Integration and Continuous Deployment (CI/CD) pipelines are particularly vulnerable, making innovative…

Graph Neural Networks (GNNs) have been shown to possess strong representation abilities over graph data. However, GNNs are vulnerable to adversarial attacks, and even minor perturbations to the graph structure can significantly degrade…