Sökning: "adversarial perturbations"
Visar resultat 1 - 5 av 11 uppsatser innehållade orden adversarial perturbations.
1. Classifying Google reCAPTCHA v2 - A study using transfer learning models and evaluating their robustness against adversarial perturbations
Magister-uppsats, Lunds universitet/Statistiska institutionen; Lunds universitet/Nationalekonomiska institutionenSammanfattning : This thesis seeks to examine the suitability and robustness of transfer learning models in creating an efficient reCAPTCHA v2 classifier, and further evaluates their performance against various adversarial attacks. Three models - DenseNet201, EfficientNetV2, and InceptionV3 - were trained and assessed, highlighting the applicability of transfer learning techniques in the classification of reCAPTCHA v2 challenges. LÄS MER
2. Comparison of Discriminative and Generative Image Classifiers
Kandidat-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : In this report a discriminative and a generative image classifier, used for classification of images with handwritten digits from zero to nine, are compared. The aim of this project was to compare the accuracy of the two classifiers in absence and presence of perturbations to the images. LÄS MER
3. Improving the Robustness of Deep Neural Networks against Adversarial Examples via Adversarial Training with Maximal Coding Rate Reduction
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : Deep learning is one of the hottest scientific topics at the moment. Deep convolutional networks can solve various complex tasks in the field of image processing. However, adversarial attacks have been shown to have the ability of fooling deep learning models. LÄS MER
4. Generation and Detection of Adversarial Attacks in the Power Grid
Uppsats för yrkesexamina på avancerad nivå, Uppsala universitet/Avdelningen för systemteknikSammanfattning : Machine learning models are vulnerable to adversarial attacks that add perturbations to the input data. Here we model and simulate power flow in a power grid test case and generate adversarial attacks for these measurements in three different ways. LÄS MER
5. Systematic Literature Review of the Adversarial Attacks on AI in Cyber-Physical Systems
Kandidat-uppsats, Linnéuniversitetet/Institutionen för datavetenskap och medieteknik (DM)Sammanfattning : Cyber-physical systems, built from the integration of cyber and physical components, are being used in multiple domains ranging from manufacturing and healthcare to traffic con- trol and safety. Ensuring the security of cyber-physical systems is crucial because they provide the foundation of the critical infrastructure, and security incidents can result in catastrophic failures. LÄS MER