End-to-end prototype of facial recognition system deployed on android devices
Fault injection framework
Report including evaluation
Application Use-case
Intruder detection: multiple devices work together to identify an intruder
Test Taker ID Verification System: use age, gender and other features to ID test taker
System details
Use EdgeFace. Implement features around this model.
OR
Use open-source facial recog app. Extend this application with a communication protocol like gRPC. Implement redundancy, and consistency between clients. Connect with server and db.
Redundancy
N-version programming (makes the most sense to me)
Recovery Blocks (but latency)
N Self-checking (acceptance test will add to latency)
Fault Categorization
Broadly, what kind of faults do we want to induce?
(1) Network: node crashes, slow processing, packet loss and jitter, network partition
(2) Software: no result, incorrect result (false positive, false negative)
Deliverables
Application Use-case
System details
OR
Redundancy
Fault Categorization
Broadly, what kind of faults do we want to induce?
(1) Network: node crashes, slow processing, packet loss and jitter, network partition (2) Software: no result, incorrect result (false positive, false negative)