Can We Generate Shellcodes via Natural Language? An Empirical Study

Open paper
Benchmark Model Rank Results
code-generation-on-shellcode-ia32CodeBERT#1BLEU-4: 91.70Exact Match Accuracy: 89.75
code-generation-on-shellcode-ia32Seq2Seq with Attention#2BLEU-4: 90.03Exact Match Accuracy: 82.92

Rank counts only results with a code link.