Results 41 to 50 of about 17,780 (281)

Distributionally Adversarial Attack

Proceedings of the AAAI Conference on Artificial Intelligence, 2019
Recent work on adversarial attack has shown that Projected Gradient Descent (PGD) Adversary is a universal first-order adversary, and the classifier adversarially trained by PGD is robust against a wide range of first-order attacks. It is worth noting that the original objective of an attack/defense model relies on a data distribution p(x), typically ...
Tianhang Zheng, Changyou Chen, Kui Ren 0001   +2 more
openaire   +3 more sources

Query complexity of adversarial attacks

CoRR, 2020
There are two main attack models considered in the adversarial robustness literature: black-box and white-box. We consider these threat models as two ends of a fine-grained spectrum, indexed by the number of queries the adversary can ask. Using this point of view we investigate how many queries the adversary needs to make to design an attack that is ...
Grzegorz Gluch, Rüdiger L. Urbanke
openaire   +3 more sources

Exploring Adversarial Robustness of LiDAR Semantic Segmentation in Autonomous Driving

Sensors, 2023
Deep learning networks have demonstrated outstanding performance in 2D and 3D vision tasks. However, recent research demonstrated that these networks result in failures when imperceptible perturbations are added to the input known as adversarial attacks.
K. T. Yasas Mahima, Asanka Perera, Sreenatha Anavatti, Matt Garratt   +3 more
doaj   +1 more source

Addressing Adversarial Machine Learning Attacks in Smart Healthcare Perspectives

, 2022
Smart healthcare systems are gaining popularity with the rapid development of intelligent sensors, the Internet of Things (IoT) applications and services, and wireless communications.
Jadidi, Z, Pal, S, Selvakkumar, A
core   +1 more source

Boosting 3D Adversarial Attacks With Attacking on Frequency

IEEE Access, 2022
Deep neural networks (DNNs) have been shown to be vulnerable to adversarial attacks in the image domain. Recently, 3D adversarial attacks, especially adversarial attacks on point clouds, have elicited mounting interest.
Binbin Liu, Jinlai Zhang, Jihong Zhu
doaj   +1 more source

Exploring Diverse Feature Extractions for Adversarial Audio Detection

IEEE Access, 2023
Although deep learning models have exhibited excellent performance in various domains, recent studies have discovered that they are highly vulnerable to adversarial attacks.
Yujin Choi, Jinseong Park, Jaewook Lee, Hoki Kim   +3 more
doaj   +1 more source

Real-Time Adversarial Attacks [PDF]

Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence, 2019
In recent years, many efforts have demonstrated that modern machine learning algorithms are vulnerable to adversarial attacks, where small, but carefully crafted, perturbations on the input can make them fail. While these attack methods are very effective, they only focus on scenarios where the target model takes static input, i.e., an attacker can ...
Yuan Gong 0001, Boyang Li 0003, Christian Poellabauer, Yiyu Shi 0001   +3 more
openaire   +2 more sources

Exploring the Impact of Conceptual Bottlenecks on Adversarial Robustness of Deep Neural Networks

IEEE Access
Deep neural networks (DNNs), while powerful, often suffer from a lack of interpretability and vulnerability to adversarial attacks. Concept bottleneck models (CBMs), which incorporate intermediate high-level concepts into the model architecture, promise ...
Bader Rasheed, Mohamed Abdelhamid, Adil Khan, Igor Menezes, Asad Masood Khatak   +4 more
doaj   +1 more source

Algebraic adversarial attacks on explainability models

Machine Learning. Engineering
Classical adversarial attacks are phrased as a constrained optimisation problem. Despite the efficacy of a constrained optimisation approach to adversarial attacks, one cannot trace how an adversarial point was generated.
Lachlan Simpson, Federico Costanza, Kyle Millar, Adriel Cheng, Cheng-Chew Lim, Hong Gunn Chew   +5 more
doaj   +1 more source

All‐Optical Reconfigurable Physical Unclonable Function for Sustainable Security

Advanced Materials, EarlyView.
An all‐optical reconfigurable physical unclonable function (PUF) is demonstrated using plasmonic coupling–induced sintering of optically trapped gold nanoparticles, where Brownian motion serves as a robust entropy source. The resulting optical PUF exhibits high encoding density, strong resistance to modeling attacks, and practical authentication ...
Jang‐Kyun Kwak, Changgyun Moon, Hyun‐Bin Yu, Sunkook Kim, Dong‐Hwan Kim   +4 more
wiley   +1 more source