Related papers: Online Template Attacks: Revisited
Side-channel analysis (SCA) poses a real-world threat by exploiting unintentional physical signals to extract secret information from secure devices. Evaluation labs also use the same techniques to certify device security. In recent years,…
Machine learning models are increasingly used in fields that require high reliability such as cybersecurity. However, these models remain vulnerable to various attacks, among which the adversarial label-flipping attack poses significant…
Backdoor attacks (BAs) are an emerging threat to deep neural network classifiers. A victim classifier will predict to an attacker-desired target class whenever a test sample is embedded with the same backdoor pattern (BP) that was used to…
Recently, spiking neural networks (SNNs), deployed on neuromorphic chips, provide highly efficient solutions on edge devices in different scenarios. However, their ability to adapt to distribution shifts after deployment has become a…
Deep neural networks (DNNs) are vulnerable to small adversarial perturbations of the inputs, posing a significant challenge to their reliability and robustness. Empirical methods such as adversarial training can defend against particular…
Path MTU Discovery (PMTUD) and IP address sharing are integral aspects of modern Internet infrastructure. In this paper, we investigate the security vulnerabilities associated with PMTUD within the context of prevalent IP address sharing…
Recently, self-supervised learning (SSL) was shown to be vulnerable to patch-based data poisoning backdoor attacks. It was shown that an adversary can poison a small part of the unlabeled data so that when a victim trains an SSL model on…
Addressing the escalating security vulnerabilities in Vision-Language-Action (VLA) models, this study investigates backdoor attacks targeting the visual pathway. We identify a core obstacle causing the failure of traditional attack…
Logic locking has been a promising solution to many hardware security threats, such as intellectual property infringement and overproduction. Due to the increased attention that threats have received, many efficient specialized attacks…
Backdoor attacks in machine learning have drawn significant attention for their potential to compromise models stealthily, yet most research has focused on homogeneous data such as images. In this work, we propose a novel backdoor attack on…
Continual Test Time Adaptation (CTTA) is a task that requires a source pre-trained model to continually adapt to new scenarios with changing target distributions. Existing CTTA methods primarily focus on mitigating the challenges of…
Online Test-Time Adaptation (OTTA) has emerged as an effective strategy to handle distributional shifts, allowing on-the-fly adaptation of pre-trained models to new target domains during inference, without the need for source data. We…
An attack graph is a method used to enumerate the possible paths that an attacker can execute in the organization network. MulVAL is a known open-source framework used to automatically generate attack graphs. MulVAL's default modeling has…
Decentralised post-training of large language models utilises data and pipeline parallelism techniques to split the data and the model. Unfortunately, decentralised post-training can be vulnerable to poisoning and backdoor attacks by one or…
We study Online Convex Optimization (OCO) with adversarial constraints, where an online algorithm must make sequential decisions to minimize both convex loss functions and cumulative constraint violations. We focus on a setting where the…
The recent discovery of the Spectre and Meltdown attacks represents a watershed moment not just for the field of Computer Security, but also of Programming Languages. This paper explores speculative side-channel attacks and their…
The proposed UniGuard is the first unified online detection framework capable of simultaneously addressing adversarial examples and backdoor attacks. UniGuard builds upon two key insights: first, both AE and backdoor attacks have to…
In response to the increasing number of devices expected in next-generation networks, a shift to over-the-air (OTA) computing has been proposed. By leveraging the superposition of multiple access channels, OTA computing enables efficient…
Attack detection problems in the smart grid are posed as statistical learning problems for different attack scenarios in which the measurements are observed in batch or online settings. In this approach, machine learning algorithms are used…
Recent advancements in deep learning-based compression techniques have surpassed traditional methods. However, deep neural networks remain vulnerable to backdoor attacks, where pre-defined triggers induce malicious behaviors. This paper…