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

In the field of cybersecurity, the ability to compute similarity scores atthe function level is import. Considering that a single binary file may containan extensive amount of functions, an effective learning framework must exhibitboth high accuracy and efficiency when handling substantial volumes of data.Nonetheless, conventional methods encounter several limitations. Firstly,accurately annotating different pairs of functions with appropriate labelsposes a significant challenge, thereby making it difficult to employ supervisedlearning methods without risk of overtraining on erroneous labels. Secondly,while SOTA models often rely on pre-trained encoders or fine-grained graphcomparison techniques, these approaches suffer from drawbacks related to timeand memory consumption. Thirdly, the momentum update algorithm utilized ingraph-based contrastive learning models can result in information leakage.Surprisingly, none of the existing articles address this issue. This researchfocuses on addressing the challenges associated with large-scale BCSD. Toovercome the aforementioned problems, we propose GraphMoco: a graph momentumcontrast model that leverages multimodal structural information for efficientbinary function representation learning on a large scale. Our approach employsa CNN-based model and departs from the usage of memory-intensive pre-trainedmodels. We adopt an unsupervised learning strategy that effectively use theintrinsic structural information present in the binary code. Our approacheliminates the need for manual labeling of similar or dissimilarinformation.Importantly, GraphMoco demonstrates exceptional performance interms of both efficiency and accuracy when operating on extensive datasets. Ourexperimental results indicate that our method surpasses the current SOTAapproaches in terms of accuracy.

GraphMoco:a Graph Momentum Contrast Model that Using Multimodel Structure Information for Large-scale Binary Function Representation Learning