Preventing Data Poisoning Attacks By Using Generative Models

Aladag, Merve; Çatak, Ferhat Özgür; Gül, Ensar

doi:10.1109/ubmyk48245.2019.8965459

Cited by 18 publications

(13 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, the attacker must solve an optimization problem to decide which regions in the input data must be changed to prevent this manipulation from being easily noticed by the human eye. By solving this optimization problem using one of the available attack methods [1,19,30,40], the attacker aims to reduce the classification performance of the model on the adversarial data as much as possible. In this study, to limit the maximum allowed perturbation for the attacker, we used ∞ norm, which is the maximum pixel difference limit between original and adversarial images.…”

Section: Capability Of the Attackermentioning

confidence: 99%

See 1 more Smart Citation

Exploiting epistemic uncertainty of the deep learning models to generate adversarial samples

Tuna

Çatak

Eskil

2022

Multimed Tools Appl

Self Cite

View full text Add to dashboard Cite

Deep neural network (DNN) architectures are considered to be robust to random perturbations. Nevertheless, it was shown that they could be severely vulnerable to slight but carefully crafted perturbations of the input, termed as adversarial samples. In recent years, numerous studies have been conducted in this new area called ``Adversarial Machine Learning” to devise new adversarial attacks and to defend against these attacks with more robust DNN architectures. However, most of the current research has concentrated on utilising model loss function to craft adversarial examples or to create robust models. This study explores the usage of quantified epistemic uncertainty obtained from Monte-Carlo Dropout Sampling for adversarial attack purposes by which we perturb the input to the shifted-domain regions where the model has not been trained on. We proposed new attack ideas by exploiting the difficulty of the target model to discriminate between samples drawn from original and shifted versions of the training data distribution by utilizing epistemic uncertainty of the model. Our results show that our proposed hybrid attack approach increases the attack success rates from 82.59% to 85.14%, 82.96% to 90.13% and 89.44% to 91.06% on MNIST Digit, MNIST Fashion and CIFAR-10 datasets, respectively.

show abstract

Section: Capability Of the Attackermentioning

confidence: 99%

“…We have released our source code on GitHub. 1 To sum up; our main contributions with this paper are:…”

Section: Introductionmentioning

confidence: 99%

Exploiting epistemic uncertainty of the deep learning models to generate adversarial samples

Tuna

Çatak

Eskil

2022

Multimed Tools Appl

Self Cite

View full text Add to dashboard Cite

show abstract

“…Adversarial machine learning is an attack technique that attempts to fool neural network models by supplying craftily manipulated input with a small difference [23]. Attackers apply model evasion attacks for phishing attacks, spams, and executing malware code in an analysis environment [24]. There are also some advantages to attackers in misclassification and misdirection of models.…”

Section: Attack To Machine Learning Algorithms: Adversarial Machine L...mentioning

confidence: 99%

“…However, to prevent this noise addition from being easily noticed, the attacker must answer an optimization problem to determine which regions in the input data (i.e., beamforming) that must be modified. By solving this optimization problem using one of the available attack, methods [24], the attacker aims to reduce the prediction performance on the manipulated data as much as possible. In this study, to limit the maximum allowed perturbation allowed for the attacker, we used l ∞ norm, which is the maximum difference limit between original and adversarial instances.…”

Section: Capability Of the Attackermentioning

confidence: 99%

Security Concerns on Machine Learning Solutions for 6G Networks in mmWave Beam Prediction

Çatak¹,

Catak²,

Kuzlu³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

6G -sixth generation-is the latest cellular technology currently under development for wireless communication systems. In recent years, machine learning algorithms have been applied widely in various fields, such as healthcare, transportation, energy, autonomous car, and many more. Those algorithms have been also using in communication technologies to improve the system performance in terms of frequency spectrum usage, latency, and security. With the rapid developments of machine learning techniques, especially deep learning, it is critical to take the security concern into account when applying the algorithms. While machine learning algorithms offer significant advantages for 6G networks, security concerns on Artificial Intelligent (AI) models is typically ignored by the scientific community so far. However, security is also a vital part of the AI algorithms, this is because the AI model itself can be poisoned by attackers. This paper proposes a mitigation method for adversarial attacks against proposed 6G machine learning models for the millimeterwave (mmWave) beam prediction using adversarial learning. The main idea behind adversarial attacks against machine learning models is to produce faulty results by manipulating trained deep learning models for 6G applications for mmWave beam prediction. We also present the adversarial learning mitigation method's performance for 6G security in mmWave beam prediction application with fast gradient sign method attack. The mean square errors (MSE) of the defended model under attack are very close to the undefended model without attack.

show abstract

“…We have selected MNIST dataset that consists of numbers from people's handwriting to provide people to understand and see changes in the data. In our previous works [3,38], we applied the generative models both for data and model poisoning attacks with limited datasets.…”

Section: Introductionmentioning

confidence: 99%

A Generative Model based Adversarial Security of Deep Learning and Linear Classifier Models

Sivaslioglu

Çatak

ŞAHİNBAŞ

2021

IJCAI

Self Cite

View full text Add to dashboard Cite

Preventing Data Poisoning Attacks By Using Generative Models

Cited by 18 publications

References 6 publications

Exploiting epistemic uncertainty of the deep learning models to generate adversarial samples

Exploiting epistemic uncertainty of the deep learning models to generate adversarial samples

Security Concerns on Machine Learning Solutions for 6G Networks in mmWave Beam Prediction

A Generative Model based Adversarial Security of Deep Learning and Linear Classifier Models

Contact Info

Product

Resources

About