Untargeted Code Authorship Evasion with Seq2Seq Transformation

2023-11-26 · Soohyeon Choi, RhongHo Jang, DaeHun Nyang, David Mohaisen

Code authorship attribution is the problem of identifying authors of programming language codes through the stylistic features in their codes, a topic that recently witnessed significant interest with outstanding performance. In this work, we present SCAE, a code authorship obfuscation technique that leverages a Seq2Seq code transformer called StructCoder. SCAE customizes StructCoder, a system designed initially for function-level code translation from one language to another (e.g., Java to C#), using transfer learning. SCAE improved the efficiency at a slight accuracy degradation compared to existing work. We also reduced the processing time by about 68% while maintaining an 85% transformation success rate and up to 95.77% evasion success rate in the untargeted setting.

📄 PDF Abstract BibTeX arXiv:2311.15366

Code (0)

등록된 구현이 없습니다.

Tasks

Authorship AttributionCode Translation Transfer Learning

Methods 이 논문이 사용한 방법론

Sigmoid Activation 설명 없음

Tanh Activation 설명 없음

LSTM An LSTM is a type of recurrent neural network that addresses the vanishing gradient problem in vanilla…

Seq2Seq Seq2Seq, or Sequence To Sequence, is a model used in sequence prediction tasks, such as language modelling and machine translation. The idea is to use one…

RoPGen: Towards Robust Code Authorship Attribution via Automatic Coding Style Transformation

2022-02-12 · Zhen Li, Guenevere, Chen, Chen Chen 외

Source code authorship attribution is an important problem often encountered in applications such as software forensics, bug fixing, and software quality analysis. Recent studies show that current source code authorship …

Authorship Attribution Bug fixing Data Augmentation Diversity+1

Band Together: Untargeted Adversarial Training with Multimodal Coordination against Evasion-based Promotion Attacks

2026-05-07 · Guanmeng Xian, Ning Yang, Philip S. Yu arxiv

Multimodal recommender systems exploit visual and textual signals to alleviate data sparsity, but this also makes them more vulnerable to evasion-based promotion attacks. Existing defenses are largely limited to single-m…

Attacking the First-Principle: A Black-Box, Query-Free Targeted Mimicry Attack on Binary Function Classifiers

2026-05-18 · Gabriel Sauger, Jean-Yves Marion, Sazzadur Rahaman, Victor Matrat 외 arxiv

Binary function classifiers play a crucial role in maintaining the security and integrity of software systems by detecting malicious code and unauthorized modifications. However, machine learning-based classifiers are vu…

Masks and Mimicry: Strategic Obfuscation and Impersonation Attacks on Authorship Verification

2025-03-24 · Kenneth Alperin, Rohan Leekha, Adaku Uchendu, Trang Nguyen 외

The increasing use of Artificial Intelligence (AI) technologies, such as Large Language Models (LLMs) has led to nontrivial improvements in various tasks, including accurate authorship identification of documents. Howeve…

Adversarial Robustness Authorship Verification

PADBen: A Comprehensive Benchmark for Evaluating AI Text Detectors Against Paraphrase Attacks

2025-11-01 · Yiwei Zha, Rui Min, Shanu Sushmita arxiv

While AI-generated text (AIGT) detectors achieve over 90\% accuracy on direct LLM outputs, they fail catastrophically against iteratively-paraphrased content. We investigate why iteratively-paraphrased text -- itself AI-…