Zobrazeno 1 - 10 of 6 490 pro vyhledávání: '"LEE, IN SOOK"'
1
Report
Generating Minimalist Adversarial Perturbations to Test Object-Detection Models: An Adaptive Multi-Metric Evolutionary Search Approach
Autor: McIntyre-Garcia, Cristopher, Heymans, Adrien, Borali, Beril, Lee, Won-Sook, Nejati, Shiva
Deep Learning (DL) models excel in computer vision tasks but can be susceptible to adversarial examples. This paper introduces Triple-Metric EvoAttack (TM-EVO), an efficient algorithm for evaluating the robustness of object-detection DL models agains
Externí odkaz: http://arxiv.org/abs/2404.17020
Zobrazit plný text záznamu
2
Report
Teaching Linguistic Justice through Augmented Reality
Autor: Varatharaj, Ashvini, Welch, Abigail, Bucholtz, Mary, Lee, Jin Sook
This position paper presents the AR Language Map, a speculative artifact designed to enhance understanding of linguistic justice among middle and high school students through augmented reality (AR) that allows students to map their linguistic experie
Externí odkaz: http://arxiv.org/abs/2404.12563
Zobrazit plný text záznamu
3
Report
On Ideal Secret-Sharing Schemes for $k$-homogeneous access structures
Autor: Kim, Younjin, Kwon, Jihye, Lee, Hyang-Sook
A $k$-uniform hypergraph is a hypergraph where each $k$-hyperedge has exactly $k$ vertices. A $k$-homogeneous access structure is represented by a $k$-uniform hypergraph $\mathcal{H}$, in which the participants correspond to the vertices of hypergrap
Externí odkaz: http://arxiv.org/abs/2309.07479
Zobrazit plný text záznamu
5
Report
Improving Siamese Based Trackers with Light or No Training through Multiple Templates and Temporal Network
Autor: Sekhavati, Ali, Lee, Won-Sook
High computational power and significant time are usually needed to train a deep learning based tracker on large datasets. Depending on many factors, training might not always be an option. In this paper, we propose a framework with two ideas on Siam
Externí odkaz: http://arxiv.org/abs/2211.13812
Zobrazit plný text záznamu
6
Report
On Insecure Uses of BGN for Privacy Preserving Data Aggregation Protocols
Autor: Lee, Hyang-Sook, Lim, Seongan, Yie, Ikkwon, Yun, Aaram
Publikováno v: Fundamenta Informaticae, Volume 188, Issue 2 (March 7, 2023) fi:9967
The notion of aggregator oblivious (AO) security for privacy preserving data aggregation was formalized with a specific construction of AO-secure blinding technique over a cyclic group by Shi et al. Some of proposals of data aggregation protocols use
Externí odkaz: http://arxiv.org/abs/2208.11304
Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání

Omezení vyhledávání
Plný text Recenzováno Digitální knihovna AV ČR
Zdroje