Security Evaluation of Pattern Classifiers under Attack

Security Evaluation of Pattern Classifiers under Attack

ABSTRACT:

Pattern classification systems are commonly used in adversarial applications, like biometric authentication, network intrusion detection, and spam filtering, in which data can be purposely manipulated by humans to undermine their operation. As this adversarial scenario is not taken into account by classical design methods, pattern classification systems may exhibit vulnerabilities,whose exploitation may severely affect their performance, and consequently limit their practical utility. Extending pattern classification theory and design methods to adversarial settings is thus a novel and very relevant research direction, which has not yet been pursued in a systematic way. In this paper, we address one of the main open issues: evaluating at design phase the security of pattern classifiers, namely, the performance degradation under potential attacks they may incur during operation. We propose a framework for empirical evaluation of classifier security that formalizes and generalizes the main ideas proposed in the literature, and give examples of its use in three real applications. Reported results show that security evaluation can provide a more complete understanding of the classifier’s behavior in adversarial environments, and lead to better design choices

EXISTING SYSTEM:

Pattern classification systems based on classical theory and design methods  do not take into account adversarial settings, they exhibit vulnerabilities to several potential attacks, allowing adversaries to undermine their effectiveness . A systematic and unified treatment of this issue is thus needed to allow the trusted adoption of pattern classifiers in adversarial environments, starting from the theoretical foundations up to novel design methods, extending the classical design cycle of . In particular, three main open issues can be identified: (i) analyzing the vulnerabilities of classification algorithms, and the corresponding attacks. (ii) developing novel methods to assess classifier security against these attacks, which is not possible using classical performance evaluation methods . (iii) developing novel design methods to guarantee classifier security in adversarial environments .       

DISADVANTAGES OF EXISTING SYSTEM:

1. Poor analyzing the vulnerabilities of classification algorithms, and the corresponding attacks.

2.A malicious webmaster may manipulate search engine rankings to artificially promote her1 website.

PROPOSED SYSTEM:

In this work we address issues  above by developing a framework for the empirical evaluation of classifier security at design phase that extends the model selection and performance evaluation steps of the classical design cycle .We summarize previous work, and point out three main ideas that emerge from it. We then formalize and generalize them in our framework (Section 3). First, to pursue security in the context of an arms race it is not sufficient to react to observed attacks, but it is also necessary to proactively anticipate the adversary by predicting the most relevant, potential attacks through a what-if analysis; this allows one to develop suitable countermeasures before the attack actually occurs, according to the principle of security by design. Second, to provide practical guidelines for simulating realistic attack scenarios, we define a general model of the adversary, in terms of her goal, knowledge, and capability, which encompasses and generalizes models proposed in previous work. Third, since the presence of carefully targeted attacks may affect the distribution of training and testing data separately, we propose a model of the data distribution that can formally characterize this behavior, and that allows us to take into account a large number of potential attacks; we also propose an algorithm for the generation of training and testing sets to be used for security evaluation,which can naturally accommodate application-specific and heuristic techniques for simulating attacks.

ADVANTAGES OF PROPOSED SYSTEM:

1.Prevents developing novel methods to assess classifier security against these attack.

2.The presence of an intelligent and adaptive adversary makes the classification problem highly non-stationary .

SYSTEM REQUIREMENTS:

HARDWARE REQUIREMENTS:

Ø System                          :         Pentium IV 2.4 GHz.

Ø Hard Disk                      :         40 GB.

Ø Floppy Drive                 :         1.44 Mb.

Ø Monitor                         :         15 VGA Colour.

Ø Mouse                            :         Logitech.

Ø Ram                               :         512 Mb.

SOFTWARE REQUIREMENTS:

Ø Operating system           :         Windows XP/7.

Ø Coding Language :         JAVA/J2EE

Ø IDE                      :         Netbeans 7.4

Ø Database              :         MYSQL

REFERENCE:

Battista Biggio, Member, IEEE , Giorgio Fumera, Member, IEEE , and Fabio Roli, Fellow, IEEE”Security Evaluation of Pattern Classifiers under Attack”IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING,VOL. 26,NO. 4,APRIL 2014.