Pith. sign in

REVIEW

Malware Sight-Seeing: Accelerating Reverse-Engineering via Point-of-Interest-Beacons

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2109.04065 v1 pith:X2SD5RXK submitted 2021-09-09 cs.CR

Malware Sight-Seeing: Accelerating Reverse-Engineering via Point-of-Interest-Beacons

classification cs.CR
keywords malwarepoisanalystautomaticallybotnetbotnetsdataengineering
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

New types of malware are emerging at concerning rates. However, analyzing malware via reverse engineering is still a time-consuming and mostly manual task. For this reason, it is necessary to develop techniques that automate parts of the reverse engineering process and that can evade the built-in countermeasures of modern malware. The main contribution of this paper is a novel method to automatically find so-called Points-of-Interest (POIs) in executed programs. POIs are instructions that interact with data that is known to an analyst. They can be used as beacons in the analysis of malware and can help to guide the analyst to the interesting parts of the malware. Furthermore, we propose a metric for POIs , the so-called confidence score that estimates how exclusively a POI will process data relevant to the malware. With the goal of automatically extract peers in P2P botnet malware, we demonstrate and evaluate our approach by applying it on four botnets (ZeroAccess, Sality, Nugache, and Kelihos). We looked into the identified POIs for known IPs and ports and, by using this information, leverage it to successfully monitor the botnets. Furthermore, using our scoring system, we show that we can extract peers for each botnet with high accuracy.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.