Presentation is loading. Please wait.

Presentation is loading. Please wait.

Hidden Markov Models for Software Piracy Detection Shabana Kazi Mark Stamp HMMs for Piracy Detection 1.

Similar presentations


Presentation on theme: "Hidden Markov Models for Software Piracy Detection Shabana Kazi Mark Stamp HMMs for Piracy Detection 1."— Presentation transcript:

1 Hidden Markov Models for Software Piracy Detection Shabana Kazi Mark Stamp HMMs for Piracy Detection 1

2 Intro  Here, we apply metamorphic analysis to software piracy detection  Very similar to techniques used in malware detection o But, problem is completely different o Has nothing to do with malware  We show that there are other applications of such techniques HMMs for Piracy Detection 2

3 Software Piracy  Software piracy is major problem o By 2009 estimate, $3 to $4 lost to piracy for every $1 in software sales  Usually, piracy consists of taking software without modification  In some cases, software is modified o Commercial theft of intellectual property o Thief really doesn’t want to get caught… HMMs for Piracy Detection 3

4 Software Piracy  We assume software is stolen o And modified, making it hard to detect o If completely rewritten from scratch, we won’t detect it by our approach  Want to make life hard for bad guys o Ideally, major modifications required  How much modification is need before we cannot reliably detect? HMMs for Piracy Detection 4

5 Goals  Technique applicable to any software  No special effort by developer o Nothing extra inserted into code  We only require access to exe file  Not a watermarking scheme o More like software “birthmark” analysis  Also not plagiarism detection o Here, want a “deeper” analysis HMMs for Piracy Detection 5

6 Use Case  You work for Alice’s Software Company o And you develop fancy software for ASC  Trudy’s Software Company (TSC) develops suspiciously similar product  You suspect TSC of stealing your code o Not identical, but seems similar  What can you do? o We’ve got some ideas that might help… HMMs for Piracy Detection 6

7 Use Case  Using the technique discussed here  Can easily measure code similarity  Low similarity? o Then no hope of proving code is stolen  High similarity? o Further (costly) analysis is warranted  High similarity does not prove stolen o But a good reason to take a closer look HMMs for Piracy Detection 7

8 Background  Metamorphic software o Metamorphic techniques (dead code, permutation, substitution)  HMM o Basic ideas and notation o The 3 problems and their solutions (discussed at a high level)  We’ve seen all of this before HMMs for Piracy Detection 8

9 Overview  Training and scoring  Train HMM on slightly morphed copies of given “base” software o Slight morphing to avoid overfitting  Score morphed copies and other files o Here, morphing serves to simulate modifications by attacker  Want to know how much morphing required before detection fails HMMs for Piracy Detection 9

10 Metamorphic Generator  Built our own metamorphic generator  Morph based on extracted opcodes o Morphing consists of dead code insertion o Specify a dead code percentage and number of blocks to insert  Do not require morphed code works o Makes detection more difficult, not easier o A worst-case scenario, detection-wise HMMs for Piracy Detection 10

11 Training  Given a base executable file…  Extract its opcode sequence  Generate 100 slightly morphed copies o Each morphed 10%, using dead code extracted from random “normal” file  Train HMM on morphed copies o Using 5-fold cross validation o Note: We train one model for each “fold” HMMs for Piracy Detection 11

12 Training  Illustration of training process o Slightly morphed copies of base program HMMs for Piracy Detection 12

13 Determine Threshold  For each of 5-folds o Train HMM o Score 20 morphed files (match set) and 15 normal (nomatch set)  Determine threshold based on scores o Threshold is highest score of normal file o Implies FPR = 0; equivalently, TNR = 1 (for the given “fold”) HMMs for Piracy Detection 13

14 Setting a Threshold  Process used to set threshold HMMs for Piracy Detection 14

15 Experiments  Want to determine robustness  For each base file tested…  Train to obtain HMM and threshold  Morph base file at various percentages o Using various morphing strategies o Refer to this morphing as tampering  Score each tampered copy o Classify, based on threshold HMMs for Piracy Detection 15

16 Experiments  Scoring tampered files HMMs for Piracy Detection 16

17 Experiment Details  For each base file o 6 models o 10 tamper percent for each o 100 files each o So, 6000 scores! HMMs for Piracy Detection 17

18 Experiment Details  Tested 10 base files, each data point o So 60,000 scores computed… HMMs for Piracy Detection 18

19 Experiment Details  Repeated entire experiment 6 times o Using different number of blocks in training phase o Training made little difference on scores o So, here we only give results where 1 block used in training phase  In total 360,000 scores computed o And 360 “models” generate o That is, 1800 HMMs (one per fold) HMMs for Piracy Detection 19

20 Results: Bar Graph HMMs for Piracy Detection 20

21 Results: 3-d Plot HMMs for Piracy Detection 21

22 Conclusions  Results look very promising o Robust  high degree of morphing required before base file undetected o Practical  only requires exe, no special effort when developing o Applies to any exe, at any time  Overall, strong software “birthmark” strategy with practical implications HMMs for Piracy Detection 22

23 Future Work  Statistical analysis somewhat weak o Results may be stronger than it appears  Many other scores/combinations of scores can be tested o Results can only get better  Consider other morphing techniques o And other file types (e.g., bytecode) o And mitigations for 1-block morphing … HMMs for Piracy Detection 23

24 References  S. Kazi and M. Stamp, Hidden Markov models for software piracy detection, Information Security Journal: A Global Perspective, 22:140-149, 2013Hidden Markov models for software piracy detection HMMs for Piracy Detection 24


Download ppt "Hidden Markov Models for Software Piracy Detection Shabana Kazi Mark Stamp HMMs for Piracy Detection 1."

Similar presentations


Ads by Google