Holistic Adversarial Robustness of Deep Learning Models
نویسندگان
چکیده
Adversarial robustness studies the worst-case performance of a machine learning model to ensure safety and reliability. With proliferation deep-learning-based technology, potential risks associated with development deployment can be amplified become dreadful vulnerabilities. This paper provides comprehensive overview research topics foundational principles methods for adversarial deep models, including attacks, defenses, verification, novel applications.
منابع مشابه
Deep Adversarial Robustness
Deep learning has recently contributed to learning state-of-the-art representations in service of various image recognition tasks. Deep learning uses cascades of many layers of nonlinear processing units for feature extraction and transformation. Recently, researchers have shown that deep learning architectures are particularly vulnerable to adversarial examples, inputs to machine learning mode...
متن کاملDeepcloak:masking Deep Neural Network Models for Robustness against Adversarial Samples
Recent studies have shown that deep neural networks (DNN) are vulnerable to adversarial samples: maliciously-perturbed samples crafted to yield incorrect model outputs. Such attacks can severely undermine DNN systems, particularly in security-sensitive settings. It was observed that an adversary could easily generate adversarial samples by making a small perturbation on irrelevant feature dimen...
متن کاملTowards Deep Learning Models Resistant to Adversarial Attacks
Recent work has demonstrated that neural networks are vulnerable to adversarial examples, i.e., inputs that are almost indistinguishable from natural data and yet classified incorrectly by the network. To address this problem, we study the adversarial robustness of neural networks through the lens of robust optimization. This approach provides a broad and unifying view on much of the prior work...
متن کاملTowards Proving the Adversarial Robustness of Deep Neural Networks
Autonomous vehicles are highly complex systems, required to function reliably in a wide variety of situations. Manually crafting software controllers for these vehicles is difficult, but there has been some success in using deep neural networks generated using machine-learning. However, deep neural networks are opaque to human engineers, rendering their correctness very difficult to prove manua...
متن کاملUnravelling Robustness of Deep Learning based Face Recognition Against Adversarial Attacks
Deep neural network (DNN) architecture based models have high expressive power and learning capacity. However, they are essentially a black box method since it is not easy to mathematically formulate the functions that are learned within its many layers of representation. Realizing this, many researchers have started to design methods to exploit the drawbacks of deep learning based algorithms q...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Proceedings of the ... AAAI Conference on Artificial Intelligence
سال: 2023
ISSN: ['2159-5399', '2374-3468']
DOI: https://doi.org/10.1609/aaai.v37i13.26797