%0 Conference Proceedings %T Attacking and Defending Dynamic Analysis System-Calls Based IDS %+ Open University of Israël %+ Ben-Gurion University of the Negev (BGU) %A Rosenberg, Ishai %A Gudes, Ehud %Z Part 3: Attacks to Software and Network Systems %< avec comité de lecture %( Lecture Notes in Computer Science %B 10th IFIP International Conference on Information Security Theory and Practice (WISTP) %C Heraklion, Greece %Y Sara Foresti %Y Javier Lopez %I Springer International Publishing %3 Information Security Theory and Practice %V LNCS-9895 %P 103-119 %8 2016-09-26 %D 2016 %R 10.1007/978-3-319-45931-8_7 %K Malware detection %K Malware obfuscation %K Decision trees %K Behavior analysis %K Camouflage algorithm %K Machine learning %Z Computer Science [cs]Conference papers %X Machine-learning augments today’s IDS capability to cope with unknown malware. However, if an attacker gains partial knowledge about the IDS’s classifier, he can create a modified version of his malware, which can evade detection. In this article we present an IDS based on various classifiers using system calls executed by the inspected code as features. We then present a camouflage algorithm that is used to modify malicious code to be classified as benign, while preserving the code’s functionality, for decision tree and random forest classifiers. We also present transformations to the classifier’s input, to prevent this camouflage - and a modified camouflage algorithm that overcomes those transformations. Our research shows that it is not enough to provide a decision tree based classifier with a large training set to counter malware. One must also be aware of the possibility that the classifier would be fooled by a camouflage algorithm, and try to counter such an attempt with techniques such as input transformation or training set updates. %G English %Z TC 11 %Z WG 11.2 %2 https://inria.hal.science/hal-01639619v1/document %2 https://inria.hal.science/hal-01639619v1/file/421627_1_En_7_Chapter.pdf %L hal-01639619 %U https://inria.hal.science/hal-01639619 %~ IFIP-LNCS %~ IFIP %~ IFIP-TC %~ IFIP-TC11 %~ IFIP-WISTP %~ IFIP-WG11-2 %~ IFIP-LNCS-9895