DE eng

Search in the Catalogues and Directories

Hits 1 – 15 of 15

1
First year of the UQ sustainable energy micromasters series: Evaluation of participation and achievement
Coffey, Felicity C.; Ashworth, Peta. - : Springer Verlag, 2019
BASE
Show details
2
CLEF ehealth 2019 evaluation lab
BASE
Show details
3
Overview of the CLEF eHealth Evaluation Lab 2019
Kelly, Liadh; Suominen, Hanna; Goeuriot, Lorraine. - : Springer Verlag, 2019
BASE
Show details
4
Leveraging knowledge graph embeddings for natural language question answering
Wang, Ruijie; Wang, Meng; Liu, Jun. - : Springer, 2019
BASE
Show details
5
Using LIP to gloss over faces in single-stage face detection networks
Abstract: This work shows that it is possible to fool/attack recent state-of-the-art face detectors which are based on the single-stage networks. Successfully attacking face detectors could be a serious malware vulnerability when deploying a smart surveillance system utilizing face detectors. In addition, for the privacy concern, it helps prevent faces being harvested and stored in the server. We show that existing adversarial perturbation methods are not effective to perform such an attack, especially when there are multiple faces in the inut image. This is because the adversarial perturbation specifically generated for one face may disrupt the adversarial perturbation for another face. In this paper, we call this problem the Instance Perturbation Interference (IPI) problem. This IPI problem is addressed by studying the relationship between the deep neural network receptive field and the adversarial perturbation. Besides the single-stage face detector, we find that the IPI problem also exists on the first stage of the Faster-RCNN, the commonly used two-stage object detector. As such, we propose the Localized Instance Perturbation (LIP) that confines the adversarial perturbation inside the Effective Receptive Field (ERF) of a target to perform the attack. Experimental results show the LIP method massively outperforms existing adversarial perturbation generation methods – often by a factor of 2 to 10.
Keyword: 1700 Computer Science; 2614 Theoretical Computer Science; Adversarial; Detection; Effective Receptive Field; Interference; Single-stage network
URL: https://espace.library.uq.edu.au/view/UQ:c945647
BASE
Hide details
6
Vertical and sequential sentiment analysis of micro-blog topic
Wan, Shuo; Li, Bohan; Zhang, Anman. - : Springer, 2018
BASE
Show details
7
DAVE: extracting domain attributes and values from text corpus
Shen, Yongxin; Li, Zhixu; Zhang, Wenling. - : Springer Verlag, 2018
BASE
Show details
8
Mining the context of citations in scientific publications
BASE
Show details
9
Overview of the CLEF eHealth evaluation lab 2018
Suominen, Hanna; Kelly, Liadh; Goeuriot, Lorraine. - : Springer International Publishing, 2018
BASE
Show details
10
The JStar language philosophy
BASE
Show details
11
Structural operational semantics through context-dependent behaviour
Colvin, Robert J.; Hayes, Ian J.. - : Elsevier North-Holland, 2011
BASE
Show details
12
Information flow analysis with Chinese text
Cheong, Paulo; Song, Dawei; Bruza, Peter. - : Springer Verlag, 2005
BASE
Show details
13
A Correlation Analysis on LSA and HAL Semantic Space Models
BASE
Show details
14
Fuzzy K-means clustering on a high dimensional semantic space
Cao, Guihong; Song, Dawei; Bruza, Peter. - : Springer Verlag, 2004
BASE
Show details
15
A natural language interpreter for the construction of conceptual schemas
Dunn, Leone; Orlowska, Maria. - : Springer Verlag, 1990
BASE
Show details

Catalogues
0
0
0
0
0
0
0
Bibliographies
0
0
0
0
0
0
0
0
0
Linked Open Data catalogues
0
Online resources
0
0
0
0
Open access documents
15
0
0
0
0
© 2013 - 2024 Lin|gu|is|tik | Imprint | Privacy Policy | Datenschutzeinstellungen ändern