English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Detecting semantically similar functions -- a crucial analysis capabilitywith broad real-world security usages including vulnerability detection,malware lineage, and forensics -- requires understanding function behaviors andintentions. This task is challenging as semantically similar functions can beimplemented differently, run on different architectures, and compiled withdiverse compiler optimizations or obfuscations. Most existing approaches matchfunctions based on syntactic features without understanding the functions'execution semantics.  We present Trex, a transfer-learning-based framework, to automate learningexecution semantics explicitly from functions' micro-traces and transfer thelearned knowledge to match semantically similar functions. Our key insight isthat these traces can be used to teach an ML model the execution semantics ofdifferent sequences of instructions. We thus train the model to learn executionsemantics from the functions' micro-traces, without any manual labeling effort.We then develop a novel neural architecture to learn execution semantics frommicro-traces, and we finetune the pretrained model to match semanticallysimilar functions.  We evaluate Trex on 1,472,066 function binaries from 13 popular softwareprojects. These functions are from different architectures and compiled withvarious optimizations and obfuscations. Trex outperforms the state-of-the-artsystems by 7.8%, 7.2%, and 14.3% in cross-architecture, optimization, andobfuscation function matching, respectively. Ablation studies show that thepretraining significantly boosts the function matching performance,underscoring the importance of learning execution semantics.

Trex: Learning Execution Semantics from Micro-Traces for Binary Similarity