Zobrazeno 1 - 10
of 205
pro vyhledávání: '"Feng, Ryan"'
Autor:
Curran, Noah T., Cho, Minkyoung, Feng, Ryan, Liu, Liangkai, Tang, Brian Jay, MohajerAnsari, Pedram, Domeke, Alkim, Pesé, Mert D., Shin, Kang G.
In the current landscape of autonomous vehicle (AV) safety and security research, there are multiple isolated problems being tackled by the community at large. Due to the lack of common evaluation criteria, several important research questions are at
Externí odkaz:
http://arxiv.org/abs/2409.03899
Autor:
Cong-Xiao Wang, Hao-Xin Liu, Hao Gu, Jin-Ying Li, Xiao-Meng Lai, Xin-Pu Fu, Wei-Wei Wang, Qiang Fu, Feng Ryan Wang, Chao Ma, Chun-Jiang Jia
Publikováno v:
Nature Communications, Vol 15, Iss 1, Pp 1-11 (2024)
Abstract The reverse water gas shift reaction can be considered as a promising route to mitigate global warming by converting CO2 into syngas in a large scale, while it is still challenging for non-Cu-based catalysts to break the trade-off between ac
Externí odkaz:
https://doaj.org/article/2d05a2e084024d93bfcb4060e045fd44
Adversarial examples threaten the integrity of machine learning systems with alarming success rates even under constrained black-box conditions. Stateful defenses have emerged as an effective countermeasure, detecting potential attacks by maintaining
Externí odkaz:
http://arxiv.org/abs/2307.16331
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. Such stateful defenses aim to defend a
Externí odkaz:
http://arxiv.org/abs/2303.06280
Autor:
Kai Xu, Jin-Cheng Liu, Wei-Wei Wang, Lu-Lu Zhou, Chao Ma, Xuze Guan, Feng Ryan Wang, Jun Li, Chun-Jiang Jia, Chun-Hua Yan
Publikováno v:
Nature Communications, Vol 15, Iss 1, Pp 1-8 (2024)
Abstract Oxygen vacancy (Ov) is an anionic defect widely existed in metal oxide lattice, as exemplified by CeO2, TiO2, and ZnO. As Ov can modify the band structure of solid, it improves the physicochemical properties such as the semiconducting perfor
Externí odkaz:
https://doaj.org/article/add58b2823f24368b87c02d6d4edb695
Preprocessing and outlier detection techniques have both been applied to neural networks to increase robustness with varying degrees of success. In this paper, we formalize the ideal preprocessor function as one that would take any input and set it t
Externí odkaz:
http://arxiv.org/abs/2205.08989
Out-of-distribution (OOD) detection plays a crucial role in ensuring the safe deployment of deep neural network (DNN) classifiers. While a myriad of methods have focused on improving the performance of OOD detectors, a critical gap remains in interpr
Externí odkaz:
http://arxiv.org/abs/2203.02586
Detecting diffusion-generated deepfake images remains an open problem. Current detection methods fail against an adversary who adds imperceptible adversarial perturbations to the deepfake to evade detection. In this work, we propose Disjoint Diffusio
Externí odkaz:
http://arxiv.org/abs/2202.05687
Publikováno v:
Advanced Science, Vol 11, Iss 10, Pp n/a-n/a (2024)
Abstract Designing reactive surface clusters at the nanoscale on metal‐oxide supports enables selective molecular interactions in low‐temperature catalysis and chemical sensing. Yet, finding effective material combinations and identifying the rea
Externí odkaz:
https://doaj.org/article/62f6471b3eed465d82fd9945c84c72b5
Using Anomaly Feature Vectors for Detecting, Classifying and Warning of Outlier Adversarial Examples
We present DeClaW, a system for detecting, classifying, and warning of adversarial inputs presented to a classification neural network. In contrast to current state-of-the-art methods that, given an input, detect whether an input is clean or adversar
Externí odkaz:
http://arxiv.org/abs/2107.00561