Trustworthy AI: From principles to practices

B Li, P Qi, B Liu, S Di, J Liu, J Pei, J Yi… - ACM Computing Surveys, 2023 - dl.acm.org
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 …

A comprehensive review on deep learning algorithms: Security and privacy issues

M Tayyab, M Marjani, NZ Jhanjhi, IAT Hashem… - Computers & …, 2023 - Elsevier
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 …

Adversarial malware binaries: Evading deep learning for malware detection in executables

B Kolosnjaji, A Demontis, B Biggio… - 2018 26th European …, 2018 - ieeexplore.ieee.org
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 …

“real attackers don't compute gradients”: bridging the gap between adversarial ml research and practice

G Apruzzese, HS Anderson, S Dambra… - … IEEE Conference on …, 2023 - ieeexplore.ieee.org
Recent years have seen a proliferation of research on adversarial machine learning.
Numerous papers demonstrate powerful algorithmic attacks against a wide variety of …

Machine learning security: Threats, countermeasures, and evaluations

M Xue, C Yuan, H Wu, Y Zhang, W Liu - IEEE Access, 2020 - ieeexplore.ieee.org
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 …

A survey of adversarial attack and defense methods for malware classification in cyber security

S Yan, J Ren, W Wang, L Sun… - … Surveys & Tutorials, 2022 - ieeexplore.ieee.org
Malware poses a severe threat to cyber security. Attackers use malware to achieve their
malicious purposes, such as unauthorized access, stealing confidential data, blackmailing …

Functionality-preserving black-box optimization of adversarial windows malware

L Demetrio, B Biggio, G Lagorio, F Roli… - IEEE Transactions on …, 2021 - ieeexplore.ieee.org
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 …

Semanticadv: Generating adversarial examples via attribute-conditioned image editing

H Qiu, C **ao, L Yang, X Yan, H Lee, B Li - Computer Vision–ECCV 2020 …, 2020 - Springer
Recent studies have shown that DNNs are vulnerable to adversarial examples which are
manipulated instances targeting to mislead DNNs to make incorrect predictions. Currently …

Defending against physically realizable attacks on image classification

T Wu, L Tong, Y Vorobeychik - arxiv preprint arxiv:1909.09552, 2019 - arxiv.org
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 …

[PDF][PDF] Anomaly Detection in the Open World: Normality Shift Detection, Explanation, and Adaptation.

D Han, Z Wang, W Chen, K Wang, R Yu, S Wang… - NDSS, 2023 - ndss-symposium.org
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 …