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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Large Language Models (LLMs) have shown promise in automated programreasoning, a crucial aspect of many security tasks. However, existing LLMarchitectures for code are often borrowed from other domains like naturallanguage processing, raising concerns about their generalization and robustnessto unseen code. A key generalization challenge is to incorporate the knowledgeof code semantics, including control and data flow, into the LLM architectures.  Drawing inspiration from examples of convolution layers exploitingtranslation symmetry, we explore how code symmetries can enhance LLMarchitectures for program analysis and modeling. We present a rigorousgroup-theoretic framework that formally defines code symmetries assemantics-preserving transformations and provides techniques for preciselyreasoning about symmetry preservation within LLM architectures. Using thisframework, we introduce a novel variant of self-attention that preservesprogram symmetries, demonstrating its effectiveness in generalization androbustness through detailed experimental evaluations across different binaryand source code analysis tasks. Overall, our code symmetry framework offersrigorous and powerful reasoning techniques that can guide the futuredevelopment of specialized LLMs for code and advance LLM-guided programreasoning tasks.

Symmetry-Preserving Program Representations for Learning Code Semantics