adversarial pattern classification

33
Department of Electrical and Electronic Engineering University of Cagliari, Italy Adversarial Pattern Classification Battista Biggio XXII cycle Advisor: prof. Fabio Roli PhD in Electronic and Computer Engineering

Upload: pra-group-university-of-cagliari

Post on 05-Dec-2014

1.559 views

Category:

Education


1 download

DESCRIPTION

Presentation of PhD Thesis by Battista Biggio

TRANSCRIPT

Page 1: Adversarial Pattern Classification

Department of Electrical and Electronic Engineering

University of Cagliari, Italy

Adversarial Pattern Classification

Battista Biggio

XXII cycle

Advisor: prof. Fabio Roli

PhD in Electronic and Computer Engineering

Page 2: Adversarial Pattern Classification

05-03-2010 Adversarial Classification - B. Biggio 2

Outline

• Problem definition

• Open issues

• Contributions of this thesis

– Experiments

• Conclusions and future works

Page 3: Adversarial Pattern Classification

05-03-2010 Adversarial Classification - B. Biggio 3

What is adversarial classification?

• Pattern recognition in security applications

– spam filtering, intrusion detection, biometrics

• Malicious adversaries aim to mislead the system

legitimate

malicious

x1

x2 f(x)

Buy viagra!

Buy vi4gr@!

Page 4: Adversarial Pattern Classification

05-03-2010 Adversarial Classification - B. Biggio 4

Open issues

1. Vulnerability identification

• potential vulnerabilities may be exploited by an

adversary to mislead the system

2. Performance evaluation under attack

• standard performance evaluation does not provide

information about the robustness of a classifier under

attack

3. Defence strategies for robust classifier design

• classification algorithms were not originally thought to

be robust against adversarial attacks

Page 5: Adversarial Pattern Classification

05-03-2010 Adversarial Classification - B. Biggio 5

Main contributions of this thesis

1. State of the art in adversarial classification

– to highlight the need for a unifying view of the

problem

2. Robustness evaluation

– to provide an estimate of the performance of a

classifier under attack

– to select a more appropriate classification model

3. Defence strategies for robust classifier design

– to improve the robustness of classifiers under attack

Page 6: Adversarial Pattern Classification

1.

State of the art

Page 7: Adversarial Pattern Classification

05-03-2010 Adversarial Classification - B. Biggio 7

State of the art

• Vulnerability identification

– Good word attacks in spam filtering [Wittel, Lowd, Graham-Cumming]

– Polymorphic and poisoning attacks in IDSs [Fogla, Lee, Kloft, Laskov]

– Possible attacks to a biometric verification system [Ratha, Jain]

• Defence strategies against specific attacks

– Good word attacks in spam filtering [Jorgensen, Nelson]

– Polymorphic and poisoning attacks in IDSs [Perdisci, Cretu]

– Spoof attacks in biometrics [Rodrigues]

• No general methodology exists to evaluate the

performance of classifiers under attack

Page 8: Adversarial Pattern Classification

05-03-2010 Adversarial Classification - B. Biggio 8

State of the art

A clear and unifying view of the problem as well

as practical guidelines for the design of classifiers

in adversarial environments do not exist yet!

Page 9: Adversarial Pattern Classification

2.

Robustness evaluation

Page 10: Adversarial Pattern Classification

05-03-2010 Adversarial Classification - B. Biggio 10

Standard performance evaluation

COLLECTED

DATA

TRAINING SET

TESTING SET

CLASSIFIER

C1

C2accuracy

Performance measures

Classification accuracy

ROC curve

Area Under the ROC curve (AUC)

Techniques

Validation

Cross validation

Bootstrap

Page 11: Adversarial Pattern Classification

05-03-2010 Adversarial Classification - B. Biggio 11

Problems

• Standard performance evaluation is likely to

provide an optimistic estimate of the

performance [Kolcz]

1. collected data may not include attacks at all

Biometric systems are not typically tested

against spoof attacks

Page 12: Adversarial Pattern Classification

05-03-2010 Adversarial Classification - B. Biggio 12

Problems

• Standard performance evaluation is likely to

provide an optimistic estimate of the

performance [Kolcz]

2. collected data may contain attacks which however

were not targeted against the system being designed

Attacks collected in spam filtering or IDSs might have

targeted systems based on different features

Page 13: Adversarial Pattern Classification

05-03-2010 Adversarial Classification - B. Biggio 13

Buy vi4gr4!Buy viagra!

Did you ever play that game

when you were a kid?

Buy vi4gr4!

Problems

It is of interest to evaluate robustness

of classifiers under different attack strength

3. Collected data does not contain attacks of different

attack strength

• e.g., number of words modified in spam e-mails

Page 14: Adversarial Pattern Classification

05-03-2010 Adversarial Classification - B. Biggio 14

0

Robustness evaluation

• Result of our robustness evaluation

– performance vs attack strength

Example

performance degradation of

text classifiers in spam filtering

under different number of

modified words

C1

C2

Standard

performance

evaluation

accuracy

Page 15: Adversarial Pattern Classification

05-03-2010 Adversarial Classification - B. Biggio 15

Robustness evaluation

• Robustness evaluation is required to have a more

complete understanding of the classifier’s performance

– We need to figure out how an adversary may attack the

classifier (security by design)

• Designing attacks may be a very difficult task

– in-depth knowledge on the specific application is required

– costly and time-consuming

• e.g., fake fingerprints

• We thus propose to simulate the effect of attacks by

modifying the feature values of malicious samples

Page 16: Adversarial Pattern Classification

05-03-2010 Adversarial Classification - B. Biggio 16

Attack simulation

• Biometric multi-modal verification system

• Potential attacks

– spoof attempts

Face

matcher

Fingerprint

matcher

Claimed

identity

Fusion module

Genuine / Impostor

s1 s2

s1

s2

+

+

Impostor

Genuine

f (x)

Fingerprint

spoof

+

Face

spoof

+

Face score

Fin

ge

rprin

t sc

ore

Page 17: Adversarial Pattern Classification

05-03-2010 Adversarial Classification - B. Biggio 17

• Text classifiers in spam filtering– binary features (presence / absence of word)

• Potential attacks– bad word obfuscation (BWO) / good word insertion (GWI)

Attack simulation

Buy viagra!

x = [0 0 1 0 0 0 0 0 …]

Buy vi4gr4!

Did you ever play that game

when you were a kid where the

little plastic hippo tries to

gobble up all your marbles?

x’ = [0 0 0 0 1 0 0 1 …]

x ' = A(x)

Page 18: Adversarial Pattern Classification

05-03-2010 Adversarial Classification - B. Biggio 18

Attack strength

• Distance in the feature space

– chosen depending on the application and features

Example

• Text classifiers in spam filtering– binary features (presence / absence of word)

Buy viagra ! … Buy vi@gr4 ! …

Hamming distance

number of words modifiedin the spam message

x = [0 0 1 0 1 …] x’ = [0 0 0 0 1 …]

d(x, x ') = 1

Page 19: Adversarial Pattern Classification

05-03-2010 Adversarial Classification - B. Biggio 19

Attack strategy A(x)

Buy viagra!

B-u-y viagra!

Buy vi4gr@!

++

+

A1(x)

A2(x)

d(x, x ') ! D

0 D

A(x) depends on the adversary’s knowledge about the classifier!

D = 1

Page 20: Adversarial Pattern Classification

05-03-2010 Adversarial Classification - B. Biggio 20

Worst case attack

• To simulate attacks which exploits knowledge

on the decision function of the classifier

f (x) = sign g(x) !+1, malicious

"1, legitimate

#$%

e.g., g(x) = wix

i+ w

0i

&

A(x) = arg minx '

g(x ')

s.t. d(x, x ') ! D

D = 1

Buy viagra!

B-u-y viagra!

Buy vi4gr@!

f (x)

+

+

+

Page 21: Adversarial Pattern Classification

05-03-2010 Adversarial Classification - B. Biggio 21

Worst case attack

• Linear classifiers / binary features

• Features which have been assigned the highest

absolute weights are modified first

buyviagra

kidgame

we

igh

tsD

Buy viagra!

Buy vi4gr@!

B-u-y vi4gr@!

B-u-y vi4gr@!

game

Page 22: Adversarial Pattern Classification

05-03-2010 Adversarial Classification - B. Biggio 22

• TREC 2007 public data set

– Training set: 10K emails

– Testing set: 10K emails

• Features: words (tokens)

• Classifiers (using differentnumber of features)

– Logistic Regression (LR)

– Linear SVM

• AUC10%

Experiments on spam filtering

Text classifiers (worst case)

0 0.1 FP

TP

Attack strength

Attack strength

Page 23: Adversarial Pattern Classification

05-03-2010 Adversarial Classification - B. Biggio 23

Mimicry attack

• To simulate attacks where no information on the

classification function is exploited

• Malicious samples are camouflaged to mimic legitimate

samples

– e.g., spoof attempts, polymorphic attacks

A(x) = argminx '

d(x ', x! )

s.t. d(x,x ') " D

D = 2+

+

+

Buy viagra!

B-u-y vi4gr@!

Buy viagra!

funny game

+

Yesterday I played a funny game…

Page 24: Adversarial Pattern Classification

05-03-2010 Adversarial Classification - B. Biggio 24

Experiments on spam filtering

Text classifiers (mimicry)

• TREC 2007 public data set

– Training set: 10K emails

– Testing set: 10K emails

• Features: words (tokens)

• Classifiers (using different

number of features)

– Logistic Regression (LR)

– Linear SVM

– Bayesian text classifier

(SpamAssassin)

– SVM with RBF kernel

Attack strength

Attack strength

Page 25: Adversarial Pattern Classification

05-03-2010 Adversarial Classification - B. Biggio 25

Experiments on intrusion

detection (mimicry)

• Data set of real network traffic (Georgia Tech, 2006)

– Training set: 20K legitimate packets

– Testing set: 20K legitimate packets + 66 distinct HTTP attacks (205packets)

• Packets are classified separately

– Features: relative byte frequencies (PAYL) [Wang]

• One-class classifiers

– Mahalanobis Distanceclassifier (MD)

– SVM with RBF kernel

• Attack strength

– Percentage of bytesmodified in a packet

0 1 2 … 2550 1 2 … 2550 1 2 … 255

Attack strength

Page 26: Adversarial Pattern Classification

05-03-2010 Adversarial Classification - B. Biggio 26

To sum up

1. The proposed methodology for robustnessevaluation extends standard performanceevaluation to adversarial applications

2. Experiments showed how this methodologymay give useful insights for the design of PRsystems in adversarial tasks• e.g., LR outperforms BayesSA, etc.

Page 27: Adversarial Pattern Classification

3.

Robust classifiers

Page 28: Adversarial Pattern Classification

05-03-2010 Adversarial Classification - B. Biggio 28

• Rationale

– Discriminant capability of features may change atoperating phase due to attacks

– Avoiding to under- or over-emphasise features may increaserobustness against attacks which exploit some knowledgeon the decision function

• Feature weighting for improved classifier robustness [Kolcz ]

– Algorithms for improving robustness of linear classifiers

– Underlying idea: to obtain more uniform set of weights

Defence strategies for robust

classifier design

buyviagra

kid

game

buy viagra

kid game

Buy viagra!

… we

igh

ts

we

igh

ts

Page 29: Adversarial Pattern Classification

05-03-2010 Adversarial Classification - B. Biggio 29

Robust classifiers by MCSs

• We investigated if bagging and RSM can beexploited to design more robust linear classifiers

• The underlying idea is still to obtain more uniformset of weights

1

Kfk (x)

k=1

K

!

f1(x) = wi

1xi + w0

1

!

fK (x) = wi

Kxi + w0

K

!

…DATA

bagging,

RSM

Page 30: Adversarial Pattern Classification

05-03-2010 Adversarial Classification - B. Biggio 30

Robust training

• Adding simulated attacks to the training set

Face

matcher

Fingerprint

matcher

Claimed

identity

Fusion module

Genuine / Impostor

s1 s2

s1

s2

+

+

ImpostorFace

spoof

Fingerprint

spoof

f (x)

+

+

Face score

Fin

ge

rprin

t sc

ore

f '(x)

Genuine

Page 31: Adversarial Pattern Classification

05-03-2010 Adversarial Classification - B. Biggio 31

Experiments on spam filtering

SpamAssassin

• SpamAssassin: open source spam filter

– Linear classifier / binary features (tests)

• default weights are manually tuned by designers to improve robustness

• TREC 2007 public data set

– First 10,000 e-mails to train the text classifier

– Second 10,000 e-mails to train the linear decision function

– Third 10,000 e-mails as testing set

URL filter

Keyword filter

Header analysis

Text classifier

…legitimate

spam

w1

w2

w3

wn

! ths

s ! th

s < th

Page 32: Adversarial Pattern Classification

05-03-2010 Adversarial Classification - B. Biggio 32

Experiments on spam filtering

SpamAssassin (worst case)

• Attack strength

– number of evaded tests

• Robust training

– to defend against worstcase attacks

• Defence strategies are noteffective against the mimicryattack

• Strategies proposed by Kolczexhibited similar results to RSMand bagging

Attack strength

Attack strength

Page 33: Adversarial Pattern Classification

05-03-2010 Adversarial Classification - B. Biggio 33

Conclusions and future works

• Adversarial pattern classification and open issues

• Contributions of this thesis– State of the art of works in adversarial classification

– Methodology for robustness evaluation

– Defence strategies for robust classifier design

• Experimental results provide useful insights for the design

of PR systems in adversarial environments

• Future works

– Theoretical investigation of adversarial classification

– Robustness evaluation of biometric verification systems