Search

Pape Maguette Sylla

from Laurel, MD
Age ~49
Get Report
Also known as:
Pape M Sylla, Sylla Pape
Related to:
Maguette PapeFatou SyllaMassire Sylla, 37Mouhamadou D Sylla, 39Aminata Sylla, 43Mamadou Sylla, 76Ibrahima Fall, 57Ibou FallBintou Sylla, 46
Connected to:
Brian P Sylla, 60Edith D Sylla, 82Ma Sylla, 45Matthew S Sylla, 37Philip M Sylla, 78Sarah Sylla, 29James A Sylora, 61Eric A Sylstad, 52Margaret A Sylte, 81Carlos R Sylva, 69

Pape Sylla Phones & Addresses

  • Laurel, MD
  • Thousand Oaks, CA
  • 6702 Lake Park Dr, Greenbelt, MD 20770 (301) 552-8282
  • 6702 Lake Park Dr APT 301, Greenbelt, MD 20770 (301) 552-8282
  • Calabasas, CA
  • 11258 Evans Trl, Beltsville, MD 20705
  • Damascus, MD
  • Silver Spring, MD
  • Sioux Falls, SD
  • 11258 Evans Trl APT 103, Beltsville, MD 20705 (301) 633-8234

Work

Company: General dynamics, fidelis security solutions Jan 2011 Position: Senior software engineer

Education

School / High School: University of Maryland 2009 Specialities: Ph.D. in Electrical Engineering

Resumes

Resumes

Pape Sylla Photo 1

Researcher

View page
Location:
205 north Conejo School Rd, Thousand Oaks, CA 91362
Industry:
Computer & Network Security
Work:
HRL Laboratories - United States since Jun 2013
Researcher
Fidelis Security Systems Jan 2011 - Jun 2013
Senior Developer
University of Maryland, College Park 2008 - 2011
Post Doc
Symantec 2002 - 2008
Senior Software Developer
Education:
University of Maryland College Park
Doctor of Philosophy (Ph.D.), Electrical Engineering
Skills:
C++
Algorithms
Software Development
C
Linux
Matlab
Software Engineering
Computer Security
Signal Processing
Network Security
Security
Sql
Programming
Research
Machine Learning
Cloud Computing
Telecommunications Engineering
Tcp/Ip Protocols
Electrical Engineering
Mathematics
Applied Physics
Tcp/Ip
Languages:
English
Pape Sylla Photo 2

Pape Sylla Damascus, MD

View page
Work:
General Dynamics, Fidelis Security Solutions

Jan 2011 to 2000
Senior Software Engineer
University of Maryland, Department of Electrical Engineering
College Park, MD
Feb 2010 to Dec 2010
Post-Doctoral Fellow
University of Maryland, Department of Electrical Engineering
College Park, MD
Jun 2008 to Feb 2010
Graduate Research Assistant/Post-Doctoral Fellow
Symantec Corporation
Alexandria, VA
Aug 2002 to Jun 2008
Senior Software Developer
Riptech Corporation
Alexandria, VA
Dec 2000 to Aug 2002
Security Consultant
National Security Agency/University of Maryland
College Park, MD
Jun 1998 to Jun 2001
Graduate Research Assistant
National Security Agency/University of Maryland
College Park, MD
Jan 1999 to Jun 1999
Undergraduate Teaching Fellow
Education:
University of Maryland
2009
Ph.D. in Electrical Engineering
University of Maryland
2001
MS in Communication and Signal Processing
University of Maryland
1999
BS in Computer Engineering and Communication
University of Maryland
1999
BS in Mathematics
Pape Sylla Photo 3

Pape Sylla

View page

Publications

Us Patents

Deep Reinforcement Learning Based Method For Surreptitiously Generating Signals To Fool A Recurrent Neural Network

View page
US Patent:
20210089891, Mar 25, 2021
Filed:
Jul 23, 2020
Appl. No.:
16/937503
Inventors:
- Malibu CA, US
Christopher Serrano - Whittier CA, US
Pape Sylla - Thousand Oaks CA, US
International Classification:
G06N 3/08
G06N 3/04
G06F 17/18
Abstract:
Described is an attack system for generating perturbations of input signals in a recurrent neural network (RNN) based target system using a deep reinforcement learning agent to generate the perturbations. The attack system trains a reinforcement learning agent to determine a magnitude of a perturbation with which to attack the RNN based target system. A perturbed input sensor signal having the determined magnitude is generated and presented to the RNN based target system such that the RNN based target system produces an altered output in response to the perturbed input sensor signal. The system identifies a failure mode of the RNN based target system using the altered output.

Automatic Generation Of Images Satisfying Specified Neural Network Classifier Properties

View page
US Patent:
20200143200, May 7, 2020
Filed:
Sep 6, 2019
Appl. No.:
16/563172
Inventors:
- Malibu CA, US
Pape Sylla - Thousand Oaks CA, US
International Classification:
G06K 9/62
G06N 3/08
Abstract:
Described is a system for automatically generating images that satisfy specific image properties. Using a code parser component, a tensor expression intermediate representation (IR) of a deep neural network code is produced. A specification describing a set of image properties is parsed in a fixed formal syntax. The tensor expression IR and the specification is input into a rewriting and analysis engine. The rewriting and analysis engine queries an external solver to obtain pixel values satisfying the specification. When pixel values satisfying the specification can be found in a fixed time period, the rewriting and analysis engine combines the pixel values into an image that satisfies the specification and outputs the image.

Systems And Methods For Context-Aware Network Message Filtering

View page
US Patent:
20200067880, Feb 27, 2020
Filed:
Aug 27, 2018
Appl. No.:
16/114160
Inventors:
- Chicago IL, US
Pape M. Sylla - Calabasas CA, US
International Classification:
H04L 29/06
Abstract:
In an example, a non-transitory machine-readable medium has instructions, which, when executed by a processor of a machine, cause the machine to perform operations including: (i) receiving a plurality of network messages transmitted within a communication network, (ii) analyzing the network messages to determine network traffic information, and (iii) determining, based on the network traffic information, a current system context from among a plurality of system contexts. Each system context indicates a respective aggregate status of devices in the communication network. The operations also include (iv) selecting, based on the current system context, a set of filtering rules from among a plurality of sets of filtering rules, (v) applying the selected set of filtering rules to the network messages to determine a subset of network messages that are acceptable for the current system context, and (vi) forwarding each network message of the subset to a destination of the network message.

Firewall Filter Rules Generation

View page
US Patent:
20180054418, Feb 22, 2018
Filed:
Aug 16, 2016
Appl. No.:
15/238661
Inventors:
- Chicago IL, US
Pape M. Sylla - Calabasas CA, US
Assignee:
THE BOEING COMPANY - Chicago IL
International Classification:
H04L 29/06
Abstract:
A method includes obtaining, at a device, packet data descriptive of authorized traffic of a network. The method also includes generating, at the device, rule elements based on the packet data. The method further includes consolidating, at the device, the rule elements based on distance measures associated with the rule elements. The method also includes generating, at the device, firewall filter rules for the network based on the consolidated rule elements.

Mapping Network Service Dependencies

View page
US Patent:
20160373535, Dec 22, 2016
Filed:
Jun 19, 2015
Appl. No.:
14/745262
Inventors:
- Chicago IL, US
Hyun Jin Kim - Calabasas CA, US
Pape Maguette Sylla - Calabasas CA, US
Ryan F. Compton - Los Angeles CA, US
International Classification:
H04L 29/08
H04L 12/24
Abstract:
Example methods and systems for mapping network service and/or application dependencies are provided. Some examples may visualize a large, complex network of network services and/or applications (e.g., Internet services and applications) and their dependencies over time. Each service (or application) may be represented as a node and the visualization may present information regarding the relationships among services and/or applications using directed edges (or lines) with varying thickness, colors, and/or line-styles depending on network data.

Mapping Network Service Dependencies

View page
US Patent:
20160119213, Apr 28, 2016
Filed:
Oct 24, 2014
Appl. No.:
14/523473
Inventors:
- Chicago IL, US
Pape Maguette Sylla - Calabasas CA, US
International Classification:
H04L 12/26
H04L 29/08
Abstract:
A method and apparatus for discovering service dependencies. A plurality of connections is identified between nodes in a data network. A set of connection pairs is identified based on the plurality of connections identified. A set of time series is created for the set of connection pairs using monitoring data received from a plurality of sensors monitoring the data network. Service dependencies may be discovered using the set of time series.
Control profile
Pape Maguette Sylla from Laurel, MD, age ~49 Get Report