Jean-Yves Marion

Gabriel Sauger, Jean-Yves Marion, Sazzadur Rahaman et al.

Binary function classifiers play a crucial role in maintaining the security and integrity of software systems by detecting malicious code and unauthorized modifications. However, machine learning-based classifiers are vulnerable to adversarial attacks that can evade detection. In this study, we present Kelpie, a novel framework for executing mimicry attacks, a stronger type of targeted evasion attacks, on binary function classifiers in a black-box, zero-query setting. Unlike previous approaches that rely on querying the target classifier to refine untargeted evasion attacks, Kelpie leverages code transformations that preserve the functionality of malicious payloads while causing them to be misclassified as we want. Through extensive experimentation, we demonstrate that Kelpie can successfully execute mimicry attacks against six state-of-the-art binary function classifiers representing different model architectures without requiring direct interaction with them. We further validate our approach with a practical demonstration, involving a keylogger and a wiper concealed within benign-looking functions embedded in an application. This work, to our best knowledge, is the first to demonstrate such a mimicry attack in a black-box, zero-query context, raising important questions about the reliability and security of existing machine learning-based binary function classifiers.

Mathilde Ollivier, Sébastien Bardin, Richard Bonichon et al.

Code obfuscation is a major tool for protecting software intellectual property from attacks such as reverse engineering or code tampering. Yet, recently proposed (automated) attacks based on Dynamic Symbolic Execution (DSE) shows very promising results, hence threatening software integrity. Current defenses are not fully satisfactory, being either not efficient against symbolic reasoning, or affecting runtime performance too much, or being too easy to spot. We present and study a new class of anti-DSE protections coined as path-oriented protections targeting the weakest spot of DSE, namely path exploration. We propose a lightweight, efficient, resistant and analytically proved class of obfuscation algorithms designed to hinder DSE-based attacks. Extensive evaluation demonstrates that these approaches critically counter symbolic deobfuscation while yielding only a very slight overhead.

Robin David, Sébastien Bardin, Jean-Yves Marion

Software deobfuscation is a crucial activity in security analysis and especially, in malware analysis. While standard static and dynamic approaches suffer from well-known shortcomings, Dynamic Symbolic Execution (DSE) has recently been proposed has an interesting alternative, more robust than static analysis and more complete than dynamic analysis. Yet, DSE addresses certain kinds of questions encountered by a reverser namely feasibility questions. Many issues arising during reverse, e.g. detecting protection schemes such as opaque predicates fall into the category of infeasibility questions. In this article, we present the Backward-Bounded DSE, a generic, precise, efficient and robust method for solving infeasibility questions. We demonstrate the benefit of the method for opaque predicates and call stack tampering, and give some insight for its usage for some other protection schemes. Especially, the technique has successfully been used on state-of-the-art packers as well as on the government-grade X-Tunnel malware -- allowing its entire deobfuscation. Backward-Bounded DSE does not supersede existing DSE approaches, but rather complements them by addressing infeasibility questions in a scalable and precise manner. Following this line, we propose sparse disassembly, a combination of Backward-Bounded DSE and static disassembly able to enlarge dynamic disassembly in a guaranteed way, hence getting the best of dynamic and static disassembly. This work paves the way for robust, efficient and precise disassembly tools for heavily-obfuscated binaries.

Guillaume Bonfante, Jean-Yves Marion, Fabrice Sabatier et al.

The propagation techniques and the payload of Duqu have been closely studied over the past year and it has been said that Duqu shared functionalities with Stuxnet. We focused on the driver used by Duqu during the infection, our contribution consists in reverse-engineering the driver: we rebuilt its source code and analyzed the mechanisms it uses to execute the payload while avoiding detection. Then we diverted the driver into a defensive version capable of detecting injections in Windows binaries, thus preventing further attacks. We specifically show how Duqu's modified driver would have detected Duqu.