Open divyapathak24 opened 1 year ago
Check with Sankalp on point 3
Function 1: Feed per instance 64 x ( FS,FD) pairs to the IF ML model Goal: Predict before the attack happens (early detection) Observations:
Next steps:
@prathyush1886
Try new functions and find one that is giving better results.
Key idea: Leverage the characteristics of flows (fs, fd) to differentiate normal and attack.
More specifically, try the functions below:
Input: 64x(FS, FD), black box function, output: distribution stats
Check fig.4 in this paper for more ideas: https://www.ndss-symposium.org/wp-content/uploads/ndss2021_7C-2_24067_paper.pdf
Success metrics:
Definitions :
FPR: It’s the probability that a positive result will be given when the true value is negative.
FNR: It’s the probability that a negative result will be given when the true value is positive.
@prathyush1886 update the meeting minutes, especially cover:
@prathyush1886 similarity for buckets with zero flows
Meeting Minutes ( 2/9/2023 ) :
Meeting Minutes ( 7/9/2023 ):
Threshold based approach for detection: Note that the following discussion is with respect to only the retransmission flows:
if a fraction of flows/ threshold (t) > 12 --> mark the instance as an attack instance
Evaluation of our detection mechanism:
Metrics: FPR and FNR Variables: threshold (t) and #consecutive instances Objective:
Task: