Author

Bin Duan

h-index 2 View on Semantic Scholar

We have 3 of 11 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Aug 2026

Towards Effective Black-Box Adversarial Attacks on Deep Code Models via Structural and Identifier Perturbations

Strike is introduced, an input-conditioned black-box adversarial robustness-testing framework that constructs and searches a hierarchical perturbation space for each input and refines the best structural variant through similarity-guided identifier substitutions drawn from dynamically constructed candidate pools.

Bin Duan, Jin-Tao Lin, D. Kim et al. · 0 citations

Preprint Aug 2026

Testing Deep Learning Library APIs via Cross-Framework Differential Fuzzing

Xamt, a cross-framework differential fuzzing approach for deep learning library APIs, constructs and tests execution-validated groups of APIs intended to implement equivalent operations across seven libraries.

Bin Duan, Rui Dong, Nai-Peng Dong et al. · 0 citations

Preprint Aug 2026

Harnessing LLMs for Document-Guided Fuzzing of Python Libraries

VistaFuzz is introduced, a document-guided fuzzing technique that uses a locally served open-sourced LLM to extract parameter specifications from API documents and generate inputs that satisfy both parameter constraints and inter-parameter dependencies.

Bin Duan, Tarek Mahmud, Meiru Che et al. · 0 citations