MétaCan
Menu
Back to cohort
Record W4377103668 · doi:10.1145/3592623

Asm2Seq: Explainable Assembly Code Functional Summary Generation for Reverse Engineering and Vulnerability Analysis

2023· article· en· W4377103668 on OpenAlex
Scarlett Taviss, Steven H. H. Ding, Mohammad Zulkernine, Philippe Charland, Sudipta Acharya

Why this work is in the frame

A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.

affAt least one author lists a Canadian institution in the pinned OpenAlex snapshot.

Bibliographic record

VenueDigital Threats Research and Practice · 2023
Typearticle
Languageen
FieldComputer Science
TopicSoftware Engineering Research
Canadian institutionsDefence Research and Development CanadaQueen's University
Fundersnot available
KeywordsComputer scienceReverse engineeringFirmwareSource codeAssembly languageAutomatic summarizationVulnerability (computing)Code reviewCode (set theory)Static program analysisLeverage (statistics)SoftwareProcess (computing)Context (archaeology)Software engineeringArtificial intelligenceProgramming languageSoftware developmentComputer securityOperating system

Abstract

fetched live from OpenAlex

Reverse engineering is the process of understanding the inner working of a software system without having the source code. It is critical for firmware security validation, software vulnerability research, and malware analysis. However, it often requires a significant amount of manual effort. Recently, data-driven solutions were proposed to reduce manual effort by identifying the code clones on the assembly or the source level. However, security analysts still have to understand the matched assembly or source code to develop an understanding of the functionality, and it is assumed that such a matched candidate always exists. This research bridges the gap by introducing the problem of assembly code summarization. Given the assembly code as input, we propose a machine-learning-based system that can produce human-readable summarizations of the functionalities in the context of code vulnerability analysis. We generate the first assembly code to function summary dataset and propose to leverage the encoder-decoder architecture. With the attention mechanism, it is possible to understand what aspects of the assembly code had the largest impact on generating the summary. Our experiment shows that the proposed solution achieves high accuracy and the Bilingual Evaluation Understudy (BLEU) score. Finally, we have performed case studies on real-life CVE vulnerability cases to better understand the proposed method’s performance and practical implications.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.004
metaresearch head score (Gemma)0.014
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesMetaresearch, Scholarly communication
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.835
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0040.014
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0010.002
Science and technology studies0.0000.000
Scholarly communication0.0010.003
Open science0.0000.000
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0000.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.174
GPT teacher head0.394
Teacher spread0.220 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it