Partial Retraining Substitute Model for Query-Limited Black-Box Attacks
Applied Sciences, 2020 Black-box attacks against deep neural network (DNN) classifiers are receiving increasing attention because they represent a more practical approach in the real world than white box attacks.
Hosung Park, Gwonsang Ryu, Daeseon Choi
doaj +2 more sources
Detecting Black-Box Model Probing Attacks Through Probability Scores
IEEE AccessIn the black-box model probing attack, the attacker sends a series of model inference requests to a victim model to map out the classification boundary of the model.
Yongzhi Wang +5 more
doaj +2 more sources
Reinforcement Learning-Based Black-Box Model Inversion Attacks [PDF]
, 2023 Model inversion attacks are a type of privacy attack that reconstructs private data used to train a machine learning model, solely by accessing the model.
Han, Gyojin +3 more
core +3 more sources
Besting the Black-Box: Barrier Zones for Adversarial Example Defense
IEEE Access, 2022 Adversarial machine learning defenses have primarily been focused on mitigating static, white-box attacks. However, it remains an open question whether such defenses are robust under an adaptive black-box adversary.
Kaleel Mahmood +4 more
doaj +1 more source
Beware the Black-Box: On the Robustness of Recent Defenses to Adversarial Examples
Entropy, 2021 Many defenses have recently been proposed at venues like NIPS, ICML, ICLR and CVPR. These defenses are mainly focused on mitigating white-box attacks. They do not properly examine black-box attacks.
Kaleel Mahmood +3 more
doaj +1 more source
Towards Lightweight Black-Box Attacks against Deep Neural Networks
, 2022 Black-box attacks can generate adversarial examples without accessing the parameters of target model, largely exacerbating the threats of deployed deep neural networks (DNNs).
Liu, Tongliang +7 more
core +2 more sources
Adversarial Examples Generation Method Based on Random Translation Transformation [PDF]
Jisuanji gongcheng, 2022 The image classification model based on Deep Neural Network(DNN) can recognize images with a recognition degree that is even higher than that of human eyes.However, it is vulnerable to attacks from adversarial examples because of the fragility of the ...
LI Zheming, ZHANG Hengwei, MA Junqiang, WANG Jindong, YANG Bo
doaj +1 more source
Stateful Defenses for Machine Learning Models Are Not Yet Secure Against Black-box Attacks [PDF]
, 2023 Recent work has proposed stateful defense models (SDMs) as a compelling strategy to defend against a black-box attacker who only has query access to the model, as is common for online machine learning platforms.
Fawaz, Kassem +5 more
core +1 more source
Knowledge-enhanced Black-box Attacks for Recommendations
, 2022 Recent studies have shown that deep neural networks-based recommender systems are vulnerable to adversarial attacks, where attackers can inject carefully crafted fake user profiles (i.e., a set of items that fake users have interacted with) into a target
Li, Qing +13 more
core +1 more source
G-MASK Facial Adversarial Attack Combining Gaussian Filtering and MASK [PDF]
Jisuanji gongchengThe rapid development of deep neural networks has led to significant success in fields such as computer vision and natural language processing. However, adversarial attacks may inhibit the performance of neural networks, posing a serious threat to the ...
Qian LI, Haiyun XIANG, Yuting ZHANG, Yun GAN, Haode LIAO
doaj +1 more source