A system-driven taxonomy of attacks and defenses in adversarial machine learning
K Sadeghi, A Banerjee… - IEEE transactions on …, 2020 - ieeexplore.ieee.org
Machine Learning (ML) algorithms, specifically supervised learning, are widely used in
modern real-world applications, which utilize Computational Intelligence (CI) as their core …
modern real-world applications, which utilize Computational Intelligence (CI) as their core …
Defenses in adversarial machine learning: A survey
Adversarial phenomenon has been widely observed in machine learning (ML) systems,
especially in those using deep neural networks, describing that ML systems may produce …
especially in those using deep neural networks, describing that ML systems may produce …
“real attackers don't compute gradients”: bridging the gap between adversarial ml research and practice
Recent years have seen a proliferation of research on adversarial machine learning.
Numerous papers demonstrate powerful algorithmic attacks against a wide variety of …
Numerous papers demonstrate powerful algorithmic attacks against a wide variety of …
[图书][B] Adversarial robustness for machine learning
Adversarial Robustness for Machine Learning summarizes the recent progress on this topic
and introduces popular algorithms on adversarial attack, defense and veri? cation. Sections …
and introduces popular algorithms on adversarial attack, defense and veri? cation. Sections …
Indicators of attack failure: Debugging and improving optimization of adversarial examples
Evaluating robustness of machine-learning models to adversarial examples is a challenging
problem. Many defenses have been shown to provide a false sense of robustness by …
problem. Many defenses have been shown to provide a false sense of robustness by …
Holistic adversarial robustness of deep learning models
Adversarial robustness studies the worst-case performance of a machine learning model to
ensure safety and reliability. With the proliferation of deep-learning-based technology, the …
ensure safety and reliability. With the proliferation of deep-learning-based technology, the …
Adversarial machine learning applied to intrusion and malware scenarios: a systematic review
Cyber-security is the practice of protecting computing systems and networks from digital
attacks, which are a rising concern in the Information Age. With the growing pace at which …
attacks, which are a rising concern in the Information Age. With the growing pace at which …
Adversarial machine learning beyond the image domain
Machine learning systems have had enormous success in a wide range of fields from
computer vision, natural language processing, and anomaly detection. However, such …
computer vision, natural language processing, and anomaly detection. However, such …
A survey on efficient methods for adversarial robustness
A Muhammad, SH Bae - IEEE Access, 2022 - ieeexplore.ieee.org
Deep learning has revolutionized computer vision with phenomenal success and
widespread applications. Despite impressive results in complex problems, neural networks …
widespread applications. Despite impressive results in complex problems, neural networks …
Improving adversarial robustness requires revisiting misclassified examples
Deep neural networks (DNNs) are vulnerable to adversarial examples crafted by
imperceptible perturbations. A range of defense techniques have been proposed to improve …
imperceptible perturbations. A range of defense techniques have been proposed to improve …