Results 41 to 50 of about 16,674 (259)

Instance attack: an explanation-based vulnerability analysis framework against DNNs for malware detection [PDF]

PeerJ Computer Science, 2023
Deep neural networks (DNNs) are increasingly being used in malware detection and their robustness has been widely discussed. Conventionally, the development of an adversarial example generation scheme for DNNs involves either detailed knowledge ...
Ruijin Sun, Shize Guo, Changyou Xing, Yexin Duan, Luming Yang, Xi Guo, Zhisong Pan   +6 more
doaj   +2 more sources

On the Geometry of Adversarial Examples

CoRR, 2018
Adversarial examples are a pervasive phenomenon of machine learning models where seemingly imperceptible perturbations to the input lead to misclassifications for otherwise statistically accurate models. We propose a geometric framework, drawing on tools from the manifold reconstruction literature, to analyze the high-dimensional geometry of ...
Marc Khoury, Dylan Hadfield-Menell
openaire   +2 more sources

Statistical Detection of Adversarial Examples in Blockchain-Based Federated Forest In-Vehicle Network Intrusion Detection Systems

IEEE Access, 2022
The internet-of-Vehicle (IoV) can facilitate seamless connectivity between connected vehicles (CV), autonomous vehicles (AV), and other IoV entities. Intrusion Detection Systems (IDSs) for IoV networks can rely on machine learning (ML) to protect the in ...
Ibrahim Aliyu, Selinde Van Engelenburg, Muhammed Bashir Mu'Azu, Jinsul Kim, Chang Gyoon Lim   +4 more
doaj   +1 more source

Adversarial Examples in the Physical World [PDF]

, 2018
Most existing machine learning classifiers are highly vulnerable to adversarial examples. An adversarial example is a sample of input data which has been modified very slightly in a way that is intended to cause a machine learning classifier to misclassify it.
Alexey Kurakin, Ian J. Goodfellow, Samy Bengio   +2 more
openaire   +3 more sources

A Framework for Robust Deep Learning Models Against Adversarial Attacks Based on a Protection Layer Approach

IEEE Access
Deep learning (DL) has demonstrated remarkable achievements in various fields. Nevertheless, DL models encounter significant challenges in detecting and defending against adversarial samples (AEs).
Mohammed Nasser Al-Andoli, Shing Chiang Tan, Kok Swee Sim, Pey Yun Goh, Chee Peng Lim   +4 more
doaj   +1 more source

Simple Transparent Adversarial Examples

CoRR, 2021
There has been a rise in the use of Machine Learning as a Service (MLaaS) Vision APIs as they offer multiple services including pre-built models and algorithms, which otherwise take a huge amount of resources if built from scratch. As these APIs get deployed for high-stakes applications, it's very important that they are robust to different ...
Jaydeep Borkar, Pin-Yu Chen
openaire   +2 more sources

Detecting Adversarial Examples

CoRR
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 approaches either focus on negating the effects of perturbations caused by the attacks to restore the DNNs' original ...
Furkan Mumcu, Yasin Yilmaz 0001
openaire   +2 more sources

Human-Producible Adversarial Examples

CoRR, 2023
Submitted to ICLR ...
David Khachaturov, Yue Gao 0011, Ilia Shumailov, Robert Mullins 0001, Ross J. Anderson, Kassem Fawaz   +5 more
openaire   +2 more sources

Theoretical Robustness Bounds on the Successful Adversarial Examples in Probabilistic Models: Comprehensive Insights From Gaussian Processes

IEEE Access
An adversarial example (AE) is an attack method targeting machine learning, which is crafted by adding an imperceptible perturbation to input data to induce misclassification.
Hiroaki Maeshima, Akira Otsuka
doaj   +1 more source

A Brute-Force Black-Box Method to Attack Machine Learning-Based Systems in Cybersecurity

IEEE Access, 2020
Machine learning algorithms are widely utilized in cybersecurity. However, recent studies show that machine learning algorithms are vulnerable to adversarial examples.
Sicong Zhang, Xiaoyao Xie, Yang Xu
doaj   +1 more source