Related papers: Replay Attack Detection Based on Parity Space Meth…
The existence of adversarial attacks on convolutional neural networks (CNN) questions the fitness of such models for serious applications. The attacks manipulate an input image such that misclassification is evoked while still looking…
This paper addresses the problem of distributed resilient state estimation and control for linear time-invariant systems in the presence of malicious false data injection sensor attacks and bounded noise. We consider a system operator…
We study continual learning in the large scale setting where tasks in the input sequence are not limited to classification, and the outputs can be of high dimension. Among multiple state-of-the-art methods, we found vanilla experience…
Supervised learning-based adversarial attack detection methods rely on a large number of labeled data and suffer significant performance degradation when applying the trained model to new domains. In this paper, we propose a self-supervised…
Active security is mainly concerned with performing one or more security functions when a host in a communication network is subject to an attack. Such security functions include appropriate actions against attackers. To properly afford…
Machine unlearning enables the removal of specific data from ML models to uphold the right to be forgotten. While approximate unlearning algorithms offer efficient alternatives to full retraining, this work reveals that they fail to…
Distributed intrustion detection systems detect attacks on computer systems by analyzing data aggregated from distributed sources. The distributed nature of the data sources allows patterns in the data to be seen that might not be…
Website fingerprinting attack is an extensively studied technique used in a web browser to analyze traffic patterns and thus infer confidential information about users. Several website fingerprinting attacks based on machine learning and…
This paper presents RADAR-Robust Adversarial Detection via Adversarial Retraining-an approach designed to enhance the robustness of adversarial detectors against adaptive attacks, while maintaining classifier performance. An adaptive attack…
Data reconstruction attacks on trained neural networks aim to recover the data on which the network has been trained and pose a significant threat to privacy, especially if the training dataset contains sensitive information. Here, we…
Local analysis has long been recognised as an effective tool to combat the state-space explosion problem. In this work, we propose a method that systematises the use of local analysis in the verification of deadlock freedom for concurrent…
This paper accelerates video perception, such as semantic segmentation and human pose estimation, by levering cross-frame redundancies. Unlike the existing approaches, which avoid redundant computations by warping the past features using…
Continual learning seeks to enable deep learners to train on a series of tasks of unknown length without suffering from the catastrophic forgetting of previous tasks. One effective solution is replay, which involves storing few previous…
Attention-based graph neural networks have made great progress in feature matching learning. However, insight of how attention mechanism works for feature matching is lacked in the literature. In this paper, we rethink cross- and…
We address the problem of allocating limited resources in a network under persistent yet statistically unknown adversarial attacks. Each node in the network may be degraded, but not fully disabled, depending on its available defensive…
Developing secure machine learning models from adversarial examples is challenging as various methods are continually being developed to generate adversarial attacks. In this work, we propose an evolutionary approach to automatically…
The generation of feasible adversarial examples is necessary for properly assessing models that work in constrained feature space. However, it remains a challenging task to enforce constraints into attacks that were designed for computer…
Deep neural networks have been proved that they are vulnerable to adversarial examples, which are generated by adding human-imperceptible perturbations to images. To defend these adversarial examples, various detection based methods have…
Reinforcement Learning (RL) agents often struggle with inefficient exploration, particularly in environments with sparse rewards. Traditional exploration strategies can lead to slow learning and suboptimal performance because agents fail to…
An enforcement mechanism monitors a reactive system for undesired behavior at runtime and corrects the system's output in case it violates the given specification. In this paper, we study the enforcement problem for hyperproperties, i.e.,…