Jin Song Dong
4 papers · Latest:
Train in Vain: Functionality-Preserving Poisoning to Prevent Unauthorized Use of Code Datasets
FunPoison introduces a functionality-preserving poisoning method to prevent unauthorized use of code datasets for training CodeLLMs, maintaining compilability.
Generalizing Test Cases for Comprehensive Test Scenario Coverage
TestGeneralizer is a framework that generalizes initial test cases to comprehensively cover diverse test scenarios, improving test coverage significantly.
Learning Project-wise Subsequent Code Edits via Interleaving Neural-based Induction and Tool-based Deduction
TRACE improves project-wise code editing by interleaving neural induction for semantic edits and tool-based deduction for syntactic edits, balancing scope, accuracy, and efficiency.
ARuleCon: Agentic Security Rule Conversion
ARuleCon is an agentic framework that automates the conversion of vendor-specific SIEM security rules, significantly reducing expert effort.
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.