Trustworthy AI: From principles to practices
The rapid development of Artificial Intelligence (AI) technology has enabled the deployment
of various systems based on it. However, many current AI systems are found vulnerable to …
of various systems based on it. However, many current AI systems are found vulnerable to …
A comprehensive review on deep learning algorithms: Security and privacy issues
Abstract Machine Learning (ML) algorithms are used to train the machines to perform
various complicated tasks that begin to modify and improve with experiences. It has become …
various complicated tasks that begin to modify and improve with experiences. It has become …
Adversarial malware binaries: Evading deep learning for malware detection in executables
Machine learning has already been exploited as a useful tool for detecting malicious
executable files. Data retrieved from malware samples, such as header fields, instruction …
executable files. Data retrieved from malware samples, such as header fields, instruction …
“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 …
Machine learning security: Threats, countermeasures, and evaluations
Machine learning has been pervasively used in a wide range of applications due to its
technical breakthroughs in recent years. It has demonstrated significant success in dealing …
technical breakthroughs in recent years. It has demonstrated significant success in dealing …
A survey of adversarial attack and defense methods for malware classification in cyber security
Malware poses a severe threat to cyber security. Attackers use malware to achieve their
malicious purposes, such as unauthorized access, stealing confidential data, blackmailing …
malicious purposes, such as unauthorized access, stealing confidential data, blackmailing …
Functionality-preserving black-box optimization of adversarial windows malware
Windows malware detectors based on machine learning are vulnerable to adversarial
examples, even if the attacker is only given black-box query access to the model. The main …
examples, even if the attacker is only given black-box query access to the model. The main …
Semanticadv: Generating adversarial examples via attribute-conditioned image editing
Recent studies have shown that DNNs are vulnerable to adversarial examples which are
manipulated instances targeting to mislead DNNs to make incorrect predictions. Currently …
manipulated instances targeting to mislead DNNs to make incorrect predictions. Currently …
Defending against physically realizable attacks on image classification
We study the problem of defending deep neural network approaches for image classification
from physically realizable attacks. First, we demonstrate that the two most scalable and …
from physically realizable attacks. First, we demonstrate that the two most scalable and …
[PDF][PDF] Anomaly Detection in the Open World: Normality Shift Detection, Explanation, and Adaptation.
Concept drift is one of the most frustrating challenges for learning-based security
applications built on the closeworld assumption of identical distribution between training and …
applications built on the closeworld assumption of identical distribution between training and …