Caleb Stewart, Rhonda Gaede, Jeffrey Kulick (University of Alabama in Huntsville)

We present DRAGON, a graph neural network (GNN) that predicts data types for decompiled variables along with a confidence estimate for each prediction. While we only train DRAGON on x64 binaries compiled without optimization, we show that DRAGON generalizes well to all combinations of the x64, x86, ARM64, and ARM architectures compiled across optimization levels O0-O3. We compare DRAGON with two state-of-the-art approaches for binary type inference and demonstrate that DRAGON exhibits a competitive or superior level of accuracy for simple type prediction while also providing useful confidence estimates. We show that the learned confidence estimates produced by DRAGON strongly correlate with accuracy, such that higher confidence predictions generally correspond with a higher level of accuracy than lower confidence predictions.

View More Papers

The State of https Adoption on the Web

Christoph Kerschbaumer (Mozilla Corporation), Frederik Braun (Mozilla Corporation), Simon Friedberger (Mozilla Corporation), Malte Jürgens (Mozilla Corporation)

Read More

Binary Code Patching: An Ancient Art Refined for the...

Dr. Barton P. Miller (Vilas Distinguished Achievement Professor at The University of Wisconsin-Madison)

Read More

NodeMedic-FINE: Automatic Detection and Exploit Synthesis for Node.js Vulnerabilities

Darion Cassel (Carnegie Mellon University), Nuno Sabino (IST & CMU), Min-Chien Hsu (Carnegie Mellon University), Ruben Martins (Carnegie Mellon University), Limin Jia (Carnegie Mellon University)

Read More

Creating Human Readable Path Constraints from Symbolic Execution

Tod Amon (Sandia National Laboratories), Tim Loffredo (Sandia National Laboratories)

Read More