Difference between revisions of "User:Snemoto"

From REU@MU
Jump to: navigation, search
Line 7: Line 7:
 
Currently working with Dr. Perouli on the project: Identifying Appropriate Machine Learning Models for Multi Robot Secure Coordination in a Healthcare Facility.
 
Currently working with Dr. Perouli on the project: Identifying Appropriate Machine Learning Models for Multi Robot Secure Coordination in a Healthcare Facility.
  
Research Interests:
+
==Weekly Logs==
 +
'''Week 1'''
 +
*Read papers on neural network inversion and HopSkipJump attacks.
 +
*Read abstracts for HumptyDumpty and MemGuard papers
 +
*Attended Orientation
 +
*Filled out pre-REU survey
 +
*Reviewed Python skills
 +
*Learned basics of Pandas and DataFrame manipulation
 +
*Learned basics of creating and evaluating machine learning models
 +
*Learned basic security considerations for applications
  
* Robots
+
 
* Adversarial Attacks
+
'''Week 2'''
* Optimal cook time for ramen noodles
+
*Attended Responsible Conduct of Research Training
 +
*Attended Technical Writing instruction session
 +
*Completed CITI Modules
 +
*Read papers:
 +
**Procedural Noise Adversarial Examples For Black-Box Attacks on Deep Convolutional Networks
 +
**Certified Robustness to Adversarial Examples with Differential Privacy.
 +
*Read introductions and conclusions for papers:
 +
**Latent Backdoor Attacks on Deep Neural Networks
 +
**Membership Inference Attacks against Adversarially Robust Deep Learning Models
 +
**Seeing isn’t Believing: Towards More Robust Adversarial Attack Against Real World Object Detectors

Revision as of 19:50, 12 June 2020

Shota Nemoto

University: Case Western Reserve University

Currently pursuing a Bachelor's degree in Computer Science

Currently working with Dr. Perouli on the project: Identifying Appropriate Machine Learning Models for Multi Robot Secure Coordination in a Healthcare Facility.

Weekly Logs

Week 1

  • Read papers on neural network inversion and HopSkipJump attacks.
  • Read abstracts for HumptyDumpty and MemGuard papers
  • Attended Orientation
  • Filled out pre-REU survey
  • Reviewed Python skills
  • Learned basics of Pandas and DataFrame manipulation
  • Learned basics of creating and evaluating machine learning models
  • Learned basic security considerations for applications


Week 2

  • Attended Responsible Conduct of Research Training
  • Attended Technical Writing instruction session
  • Completed CITI Modules
  • Read papers:
    • Procedural Noise Adversarial Examples For Black-Box Attacks on Deep Convolutional Networks
    • Certified Robustness to Adversarial Examples with Differential Privacy.
  • Read introductions and conclusions for papers:
    • Latent Backdoor Attacks on Deep Neural Networks
    • Membership Inference Attacks against Adversarially Robust Deep Learning Models
    • Seeing isn’t Believing: Towards More Robust Adversarial Attack Against Real World Object Detectors