1. RHMD: Evasion-Resilient Hardware Malware Detectors
Khaled N. Khasawneh*, Nael Abu-Ghazaleh*, Dmitry Ponomarev**, Lei Yu**
University of California, Riverside *, Binghamton University **
MICRO 2017 – Boston, USA, October 2017

2. Malware is Everywhere!

3. Over 250,000 malware registered every day!
Malware is Everywhere!
Over 250,000 malware registered every day!

4. Traditional Software Malware Detection
Static malware detection
Search for signatures in the executable
Can detect all known malware with no false alarms
Can be evaded by new malware and polymorphic malware
Dynamic malware detection
Monitors the behavior of the program
Can detect unknown malware
Very high overhead limiting use in practice

5. Hardware Malware Detectors (HMDs)
Use Machine Learning: detect malware as computational anomaly
Use low-level features collected from the hardware
Can be always-on without adding performance overhead
Many research papers including ISCA’13, HPCA’15 and MICRO’16

6. Paper Contributions Can malware evade HMDs? Reverse-engineer HMDs
Develop evasive malware
Evade detection after re-training

7. Can we make HMDs robust to evasion?
Paper Contributions
Can malware evade HMDs?
If yes
Can we make HMDs robust to evasion?
Reverse-engineer HMDs
1- Provably harder to reverse-engineer
2- Robust to evasion
Yes! Using RHMDs
Develop evasive malware
Evade detection after re-training

8. Reverse Engineering

9. How to Reverse Engineer HMDs?
Challenges:
We don’t know the detection period
We don’t know the features used
We don’t know the detection algorithm
Approach:
Train different classifiers
Derive specific parameters as an optimization problem

10. Reverse Engineering HMDs
Attacker Training Data
_________________________

11. Reverse Engineering HMDs
Victim HMD
Attacker Training Data
_________________________
10100
Black box
output

12. Reverse Engineering HMDs
Victim HMD
Attacker Training Data
_________________________
10100
Black box
output
Training model
Data
Labels

13. Reverse Engineering HMDs
Victim HMD
Attacker Training Data
_________________________
10100
Black box
output
Training model
Data
Labels
Reverse-engineered HMD

14. We Can Guess Detectors Parameters!
Victim HMD parameters:
- 10K detection period Instructions features vector

15. We Can Guess Detectors Parameters!
Victim HMD parameters:
- 10K detection period Instructions features vector
Guessing detection period:
LR: Logistic Regression
DT: Decision Tree
SVM: Support Vector Machines

16. We Can Guess Detectors Parameters!
Victim HMD parameters:
- 10K detection period Instructions features vector
Guessing feature vector:
LR: Logistic Regression
DT: Decision Tree
SVM: Support Vector Machines

17. Reverse Engineering Effectiveness
Logistic Regression
Neural Networks

18. Reverse Engineering Effectiveness
Current generation of HMDs can be reverse engineered
Logistic Regression
Neural Networks

19. Evading HMDs

20. How to Create Evasive Malware?
Challenges:
- We don’t have malware source code
- We can’t decompile malware because its obfuscated
Our approach:
PIN
Dynamic Control Flow Graph

21. What we Should Add to Evade?
Logistic Regression (LR)
LR is defined by a weight vector θ
Add instructions whose weights are negative

22. What we Should Add to Evade?
Neural Network (NN)
Collapse the description of the NN into a single vector
Add instructions whose weights are negative

23. What we Should Add to Evade?
Current generation of HMDs are vulnerable to evasion attacks!
Neural Network (NN)
Collapse the description of the NN into a single vector
Add instructions whose weights are negative

24. Does re-training Help?

25. Can we Retrain with Samples of Evasive Malware?
Linear Model
Logistic Regression

26. Can we Retrain with Samples of Evasive Malware?
Linear Model
Logistic Regression
Non-Linear Model
Neural Network

27. Explaining Retraining Performance
Linear Model (LR)

28. Explaining Retraining Performance
Non-Linear Model (NN)

29. What if we Keep Retraining?

30. What if we Keep Retraining?

31. What if we Keep Retraining?

32. What if we Keep Retraining?

33. What if we Keep Retraining?
Re-training is not a general solution

34. Can we Build Detectors that Resist Evasion?

35. Overview of RHMDs
RHMD
HMD 1
HMD 2
Pool of diverse
HMDs .
HMD n

36. Overview of RHMDs
RHMD
HMD 1
HMD 2
Input
Output .
HMD n
Selector

37. Overview of RHMDs … RHMD . Features vector Input Output
Detection period
Number of committed instructions …
Features vector
RHMD
HMD 1
HMD 2
Input
Output .
HMD n
Selector

38. Overview of RHMDs … … RHMD . Features vector Input Output
Detection period
Number of committed instructions … …
Features vector
RHMD
HMD 1
HMD 2
Input
Output .
HMD n
Selector

39. Overview of RHMDs … … … RHMD . Features vector Input Output
Detection period
Number of committed instructions … … …
Features vector
RHMD
HMD 1
HMD 2
Input
Output .
HMD n
Selector

40. Overview of RHMDs … … … RHMD Diversify by Different: 1- Features
Detection period
Number of committed instructions … … …
Features vector
RHMD
Diversify by Different:
1- Features
2- Detection periods
HMD 1
HMD 2 .
HMD n
Selector

41. Reverse Engineer RHMDs
Randomizing the features
(a) Two feature vectors
(b) Three feature vectors

42. Reverse Engineer RHMDs
Randomizing the features and detection period
(a) Two feature vectors and two periods
(b) Three feature vectors and two periods

43. RHMD is Resilient to Evasion

44. Hardware Overhead FPGA prototype on open core (AO486):
RHMD with three detectors:
Area increase 1.72%
Power increase 0.78%

45. Conclusion Current generation of HMDs vulnerable to evasion
Developed a methodology to reverse-engineer and evade detectors
Explored Re-training HMDs
Benefit is limited
Developed new class of Evasion-Resilient HMDs
Robust to evasion
Low overhead

46. RAID 2015 – Kyoto, Japan, November 2015
Thank you!
Questions?
RAID 2015 – Kyoto, Japan, November 2015

47. Can’t Just Randomly Add Instructions

48. Evasion Overhead