Results 31 to 40 of about 5,384,791 (287)
Closeness and uncertainty aware adversarial examples detection in adversarial machine learning
Computers and Electrical Engineering, 2022 While state-of-the-art Deep Neural Network (DNN) models are considered to be robust to random perturbations, it was shown that these architectures are highly vulnerable to deliberately crafted perturbations, albeit being quasi-imperceptible. These vulnerabilities make it challenging to deploy DNN models in security-critical areas. In recent years, many
Ömer Faruk Tuna +2 more
openaire +4 more sources
, 2021 Adversarial examples are input examples that are specifically crafted to deceive machine learning classifiers. State-of-the-art adversarial example detection methods characterize an input example as adversarial either by quantifying the magnitude of ...
Arora, Sunpreet S +3 more
core +1 more source
Detection of Physical Adversarial Attacks on Traffic Signs for Autonomous Vehicles [PDF]
, 2023 Current vision-based detection models within Autonomous Vehicles, can be susceptible to changes within the physical environment, which cause unexpected issues. Physical attacks on traffic signs could be malicious or naturally occurring, causing incorrect
Radoglou-Grammatikis, P. +4 more
core +1 more source
On the (Statistical) Detection of Adversarial Examples
CoRR, 2017 Machine Learning (ML) models are applied in a variety of tasks such as network intrusion detection or Malware classification. Yet, these models are vulnerable to a class of malicious inputs known as adversarial examples. These are slightly perturbed inputs that are classified incorrectly by the ML model.
Kathrin Grosse +4 more
openaire +2 more sources
Frontiers in Energy Research, 2023 The energy trading market that can support free bidding among electricity users is currently the key method in smart grid demand response. Reinforcement learning is used to formulate optimal strategies for them to obtain optimal strategies. Non-etheless,
Donghe Li +5 more
doaj +1 more source
Unsupervised Detection of Adversarial Examples with Model Explanations
CoRR, 2021 Deep Neural Networks (DNNs) have shown remarkable performance in a diverse range of machine learning applications. However, it is widely known that DNNs are vulnerable to simple adversarial perturbations, which causes the model to incorrectly classify inputs.
Gihyuk Ko, Gyumin Lim
openaire +3 more sources
GAT: Generative Adversarial Training for Adversarial Example Detection and Robust Classification [PDF]
, 2022 The vulnerabilities of deep neural networks against adversarial examples have become a significant concern for deploying these models in sensitive domains.
Kolouri, Soheil +2 more
core +1 more source
Adversarial Traffic Detection Method Based on Ensemble Learning and Anomaly Detection [PDF]
Jisuanji gongchengIn recent years, deep learning technology has been increasingly used for malicious traffic detection. However, adversarial example attacks pose challenges to deep learning-based malicious traffic detection. To address this problem, this study proposes an
DONG Fanghe, SHI Qiong, SHI Zhibin
doaj +1 more source
Towards Black-box Adversarial Example Detection: A Data Reconstruction-based Method [PDF]
, 2023 Adversarial example detection is known to be an effective adversarial defense method. Black-box attack, which is a more realistic threat and has led to various black-box adversarial training-based defense methods, however, does not attract considerable ...
Lin, Zhiyu +3 more
core +1 more source
Remote Sensing, 2023 Object detection in remote sensing has developed rapidly and has been applied in many fields, but it is known to be vulnerable to adversarial attacks. Improving the robustness of models has become a key issue for reliable application deployment.
Yang Li +5 more
doaj +1 more source