SLIDE 1
Non-Profiled Deep Learning-based Side-Channel attacks with - - PDF document
Non-Profiled Deep Learning-based Side-Channel attacks with - - PDF document
Non-Profiled Deep Learning-based Side-Channel attacks with Sensitivity Analysis Benjamin Timon August 28, 2019 Python notebook presentation for CHES 2019 1 Introduction & Motivation Profiled vs Non-Profiled attacks Machine Learning trend
SLIDE 2
SLIDE 3
This research
3
SLIDE 4
Differential Deep Learning Analysis (DDLA)
Correlation Power Analysis Follow similar strategy for DDLA
4
SLIDE 5
Demonstration: attack with accuracy and loss
Generate simulation traces
■♥ ❬✶❪✿ ❢r♦♠ ❞❡♠♦ ✐♠♣♦rt ❣❡♥❴s✐♠✉❴❞❛t❛ ★ ●❡♥❡r❛t❡ s✐♠✉❧❛t✐♦♥ tr❛❝❡s ❢♦r ❞❡♠♦♥str❛t✐♦♥ ❞❛t❛❴tr❛✐♥✐♥❣ ❂ ❣❡♥❴s✐♠✉❴❞❛t❛✭✮
Network
5
SLIDE 6
Observe loss and accuracy during training
■♥ ❬✷❪✿ ❢r♦♠ ❞❡♠♦ ✐♠♣♦rt ❞❡♠♦❴❞❞❧❛❴❛❝❝❴❧♦ss ❞❞❧❛ ❂ ❞❡♠♦❴❞❞❧❛❴❛❝❝❴❧♦ss✭❞❛t❛❴tr❛✐♥✐♥❣✮ ❞❞❧❛✳r✉♥✭♥❴❡♣♦❝❤s❂✸✵✮ ❞❞❧❛✳❢✐❣ ❖✉t❬✷❪✿
Sensitivity Analysis
6
SLIDE 7
Demonstration: Observe first layer gradient
■♥ ❬✸❪✿ ❢r♦♠ ♣❧♦ts ✐♠♣♦rt ♣❧♦t❴✇❡✐❣❤ts❴❛♥❞❴❣r❛❞❴✸❞ ♣❧♦t❴✇❡✐❣❤ts❴❛♥❞❴❣r❛❞❴✸❞✭❞❛t❛❴tr❛✐♥✐♥❣✮ ❖✉t❬✸❪✿
Observe first layer gradient during training
■♥ ❬✹❪✿ ❢r♦♠ ❞❡♠♦ ✐♠♣♦rt ❞❡♠♦❴❞❞❧❛❴❣r❛❞✐❡♥t ❞❞❧❛ ❂ ❞❡♠♦❴❞❞❧❛❴❣r❛❞✐❡♥t✭❞❛t❛❴tr❛✐♥✐♥❣✮ ❞❞❧❛✳r✉♥✭✶✺✮ ❞❞❧❛✳❢✐❣ ❖✉t❬✹❪✿ 7
SLIDE 8
■♥ ❬✺❪✿ ❢r♦♠ ♣❧♦ts ✐♠♣♦rt ♣❧♦t❴✇❡✐❣❤ts❴✷❞ ♣❧♦t❴✇❡✐❣❤ts❴✷❞✭❞❞❧❛✮ 8
SLIDE 9
❖✉t❬✺❪✿
Derivatives with regards to the inputs
9
SLIDE 10
Masked implementations
Generate masked simulation traces
■♥ ❬✻❪✿ ❢r♦♠ ❞❡♠♦ ✐♠♣♦rt ❣❡♥❴s✐♠✉❴♠❛s❦❡❞❴❞❛t❛ ★ ●❡♥❡r❛t❡ ♠❛s❦❡❞ s✐♠✉❧❛t✐♦♥ tr❛❝❡s ❢♦r ❞❡♠♦♥str❛t✐♦♥ ❞❛t❛❴tr❛✐♥✐♥❣ ❂ ❣❡♥❴s✐♠✉❴♠❛s❦❡❞❴❞❛t❛✭✮
Demonstration: high-order DDLA
■♥ ❬✼❪✿ ❢r♦♠ ❞❡♠♦ ✐♠♣♦rt ❞❡♠♦❴❞❞❧❛❴❤✐❣❤❴♦r❞❡r ❞❞❧❛ ❂ ❞❡♠♦❴❞❞❧❛❴❤✐❣❤❴♦r❞❡r✭❞❛t❛❴tr❛✐♥✐♥❣✮ ❞❞❧❛✳r✉♥✭✷✵✮ ❞❞❧❛✳❢✐❣ ❖✉t❬✼❪✿ 10
SLIDE 11
■♥ ❬✽❪✿ ❢r♦♠ ♣❧♦ts ✐♠♣♦rt ♣❧♦t❴✇❡✐❣❤ts❴✷❞ ♣❧♦t❴✇❡✐❣❤ts❴✷❞✭❞❞❧❛✮ ❖✉t❬✽❪✿ 11
SLIDE 12
12
SLIDE 13
13
SLIDE 14