Hojjat Aghakhani (University of California, Santa Barbara), Fabio Gritti (University of California, Santa Barbara), Francesco Mecca (Università degli Studi di Torino), Martina Lindorfer (TU Wien), Stefano Ortolani (Lastline Inc.), Davide Balzarotti (Eurecom), Giovanni Vigna (University of California, Santa Barbara), Christopher Kruegel (University of California, Santa Barbara)

Machine learning techniques are widely used in addition to signatures and heuristics to increase the detection rate of anti-malware software, as they automate the creation of detection models, making it possible to handle an ever-increasing number of new malware samples. In order to foil the analysis of anti-malware systems and evade detection, malware uses packing and other forms of obfuscation. However, few realize that benign applications use packing and obfuscation as well, to protect intellectual property and prevent license abuse.

In this paper, we study how machine learning based on static analysis features operates on packed samples. Malware researchers have often assumed that packing would prevent machine learning techniques from building effective classifiers. However, both industry and academia have published results that show that machine-learning-based classifiers can achieve good detection rates, leading many experts to think that classifiers are simply detecting the fact that a sample is packed, as packing is more prevalent in malicious samples. We show that, different from what is commonly assumed, packers do preserve some information when packing programs that is “useful” for malware classification. However, this information does not necessarily capture the sample’s behavior. We demonstrate that the signals extracted from packed executables are not rich enough for machine-learning-based models to (1) generalize their knowledge to operate on unseen packers, and (2) be robust against adversarial examples. We also show that a naïve application of machine learning techniques results in a substantial number of false positives, which, in turn, might have resulted in incorrect labeling of ground-truth data used in past work.

View More Papers

You Are What You Do: Hunting Stealthy Malware via...

Qi Wang (University of Illinois Urbana-Champaign), Wajih Ul Hassan (University of Illinois Urbana-Champaign), Ding Li (NEC Laboratories America, Inc.), Kangkook Jee (University of Texas at Dallas), Xiao Yu (NEC Laboratories America, Inc.), Kexuan Zou (University Of Illinois Urbana-Champaign), Junghwan Rhee (NEC Laboratories America, Inc.), Zhengzhang Chen (NEC Laboratories America, Inc.), Wei Cheng (NEC Laboratories America,…

Read More

Bobtail: Improved Blockchain Security with Low-Variance Mining

George Bissias (University of Massachusetts Amherst), Brian N. Levine (University of Massachusetts Amherst)

Read More

Adversarial Classification Under Differential Privacy

Jairo Giraldo (University of Utah), Alvaro Cardenas (UC Santa Cruz), Murat Kantarcioglu (UT Dallas), Jonathan Katz (George Mason University)

Read More

MassBrowser: Unblocking the Censored Web for the Masses, by...

Milad Nasr (University of Massachusetts Amherst), Hadi Zolfaghari (University of Massachusetts Amherst), Amir Houmansadr (University of Massachusetts Amherst), Amirhossein Ghafari (University of Massachusetts Amherst)

Read More