Page 16 - Issue265
P. 16

265
                         ـه1445 رفــــس�  ددـــــ                     ـــــعلا                                   Forum                       16
                        م2023 س�طس�غأا



















          Recently, in July 2023, the researchers from the Security Engineering   PSU's Research Achievements for the Second
          Lab (SEL) at Prince Sultan university has been awarded the “Copyright
          Registration Certificate” for the software ASParse –V3 (Auto Static   Quarter of 2023
          Parsing Tool- Version 3) from the Saudi Authority for Intellectual
          Property (SAIP).

          The authors  of  ASParse –V3  are  Dr.  Iman  Almomani,  Eng.  Rahaf
          Alkhadra, Eng. Muhannad Qasem, Eng. Tala Almashat and Dr. Walid
          Elshafai.

          ASParse-V3  is  a  GUI-based  cross-platform  static  analysis  tool.  It
          supports customization in the analysis process, where users can input
          their files and customize the scanning features, such as keywords
          and  file  types.  The  application  also  allows  users  to  export  the
          scanning results and visualize them using the interactive dashboards.
          ASParse-V3 can parse thoroughly any given file. This can be utilized
          as  a  preprocessing  step  to  extract  features,  apply  static  analysis,
          generate datasets, and train machine learning models. In addition,
          ASParse V3  offers  features  exportation  of  the  scanning  results  to
          different  file  formats,  including  JSON  and  CSV  files.  ASParseV3 is
          developed to meet market requirements while improving traditional
          static analysis application. ASParse-V3 is a better tool than others,
          because it is cross-platform and portable in that it performs static
          analysis  and  features  parsing  of  different  file  systems  for  many
          operating  systems.  In  addition,  this  version  of  ASParse  is  efficient
          and fast due to its use of concurrent scanning. ASParse-V3 can parse
          any file type, extracting static features, efficient malware analysis,
          constructing datasets of static features, and preprocessing datasets
          for ML training.  ASParse-V3  has  many  applications  including,
          Cybersecurity  Desktop  applications,  File  Parsing,  Malware  Static
          Analysis, Features extractions, Datasets generation.  RIC is pleased to share PSU's research achievements for the second quarter of 2023. Compared with data from the first quarter
          The registration of these copyright works is an important milestone   of 2023:
          for  the  SEL  Lab  and  Prince  Sultan  University.  We  would  like  to   ● Scopus publications increased by 43.6% (555 in Q1 2023)
          congratulate the team on their remarkable achievement!  ● Active researchers increased by 20.8% (130 in Q1 2023)


          First PSU Paper Accepted In CVPR



                                                                                                          Researchers  from  Prince  Sultan  University  have  accomplished  a
                                                                                                          significant milestone in high-resolution image dehazing with their
                                                                                                          latest  CVPR2023  paper,  "Streamlined  Global  and  Local  Features
                                                                                                          Combinator (SGLC) for High-Resolution Image Dehazing," developed
                                                                                                          by  an  outstanding  team  including  Bilel  Benjdira  (Ph.D.,  SMIEEE),
                                                                                                          Anas M. Ali, and Anis Koubaa.
                                                                                                          The  innovative  SGLC  approach  from  Prince  Sultan  University's
                                                                                                          research team optimizes dehazing models using two consecutive
                                                                                                          blocks, GFG and LFE, achieving significant improvements in the PSNR
                                                                                                          metric and demonstrating adaptability with various architectures.

                                                                                                          Read the paper:
                                                                                                          https://lnkd.in/gxbtQZ3G
                                                                                                          The  researchers  also  secured  a  notable  5th  position  among  17
                                                                                                          shortlisted  participants  in  the  fiercely  competitive  NTIRE  Non-
                                                                                                          Homogeneous  Dehazing  Challenge2023.  This  achievement
                                                                                                          showcases the effectiveness of the SGLC model in tackling intricate
                                                                                                          dehazing tasks and emphasizes the team's unwavering commitment
                                                                                                          to advancing the field.
   11   12   13   14   15   16   17   18   19   20   21