Fine-tuning CodeT5 to produce obfuscated XSS payloads and adding them to training data is reported to restore random-forest XSS detection accuracy from 81.9% to 99.5%, though the evaluation setup leaves the improvement unproven.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Leveraging LLM to Strengthen ML-Based Cross-Site Scripting Detection
Fine-tuning CodeT5 to produce obfuscated XSS payloads and adding them to training data is reported to restore random-forest XSS detection accuracy from 81.9% to 99.5%, though the evaluation setup leaves the improvement unproven.