Invention Grant
- Patent Title: Techniques to detect perturbation attacks with an actor-critic framework
-
Application No.: US16103137Application Date: 2018-08-14
-
Publication No.: US10726134B2Publication Date: 2020-07-28
- Inventor: Shih-Han Wang , Yonghong Huang , Micah Sheller , Cory Cornelius
- Applicant: INTEL CORPORATION
- Applicant Address: US CA Santa Clara
- Assignee: INTEL CORPORATION
- Current Assignee: INTEL CORPORATION
- Current Assignee Address: US CA Santa Clara
- Main IPC: G06F21/57
- IPC: G06F21/57 ; G06N5/04 ; G06F21/56 ; G06N20/00 ; G06N3/08 ; G06F21/55 ; G06N3/00 ; G06N3/04

Abstract:
Embodiments discussed herein may be generally directed to systems and techniques to generate a quality score based on an observation and an action caused by an actor agent during a testing phase. Embodiments also include determining a temporal difference between the quality score and a previous quality score based on a previous observation and a previous action, determining whether the temporal difference exceeds a threshold value, and generating an attack indication in response to determining the temporal difference exceeds the threshold value.
Public/Granted literature
- US20190042761A1 TECHNIQUES TO DETECT PERTURBATION ATTACKS WITH AN ACTOR-CRITIC FRAMEWORK Public/Granted day:2019-02-07
Information query