Essays about: "Adversarial Examples"
Showing result 6 - 10 of 15 essays containing the words Adversarial Examples.
-
6. Improving the Robustness of Deep Neural Networks against Adversarial Examples via Adversarial Training with Maximal Coding Rate Reduction
University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)Abstract : 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. READ MORE
-
7. Systematic Literature Review of the Adversarial Attacks on AI in Cyber-Physical Systems
University essay from Linnéuniversitetet/Institutionen för datavetenskap och medieteknik (DM)Abstract : 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. READ MORE
-
8. Evaluating Robustness of a CNN Architecture introduced to the Adversarial Attacks
University essay from Blekinge Tekniska HögskolaAbstract : Abstract: Background: From Previous research, state-of-the-art deep neural networks have accomplished impressive results on many images classification tasks. However, adversarial attacks can easily fool these deep neural networks by adding little noise to the input images. READ MORE
-
9. Adversarial Example Transferabilty to Quantized Models
University essay from Linköpings universitet/Medie- och Informationsteknik; Linköpings universitet/Tekniska fakultetenAbstract : Deep learning has proven to be a major leap in machine learning, allowing completely new problems to be solved. While flexible and powerful, neural networks have the disadvantage of being large and demanding high performance from the devices on which they are run. READ MORE
-
10. Navigating Deep Classifiers : A Geometric Study Of Connections Between Adversarial Examples And Discriminative Features In Deep Neural Networks
University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)Abstract : Although deep networks are powerful and effective in numerous applications, their high vulnerability to adversarial perturbations remains a critical limitation in domains such as security, personalized medicine or autonomous systems. While the sensitivity to adversarial perturbations is generally viewed as a bug of deep classifiers, recent research suggests that they are actually a manifestation of non-robust features that deep classifiers exploit for predictive accuracy. READ MORE
