Enregistré dans:
| Auteurs principaux: | , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | https://arxiv.org/abs/2605.07269 |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866910200569528320 |
|---|---|
| author | Muhtadi, Al Muhit Tazwar, Mostafa Rifat |
| author_facet | Muhtadi, Al Muhit Tazwar, Mostafa Rifat |
| contents | Indirect prompt injection remains a persistent weakness in retrieval-augmented and tool-using LLM systems, and the problem becomes harder to characterise in multilingual settings. We present MIPIAD, a defense framework evaluated on English and Bangla that combines a sequence classifier fine-tuned from Qwen2.5-1.5B via LoRA (XLPID), TF-IDF lexical features, and validation-tuned ensembling through late fusion, stacking, and gradient boosting. The framework is evaluated on a synthetic benchmark built from BIPIA(Yi et al., 2023) templates spanning five task families -- email, table, QA, abstract, and code-comprising over 1.43 million generated samples, with train and test splits using mutually exclusive attack categories. Across the experiments, lexical signals prove strong (TF-IDF+SVM F1=0.77), and the hybrid XLPID+TF-IDF ensemble achieves the best overall F1 (0.9205) while the Boosting Ensemble achieves the best AUROC (0.9378). Ensemble methods consistently reduce the English-Bangla cross-lingual gap relative to standalone neural models. The pipeline is designed for extensibility: NLLB-200 supports over 200 languages and XLPID's multilingual backbone can be retargeted to additional languages without architectural changes; empirical validation is currently limited to English and Bangla |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_07269 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | MIPIAD: Multilingual Indirect Prompt Injection Attack Defense with Qwen -- TF-IDF Hybrid and Meta-Ensemble Learning Muhtadi, Al Muhit Tazwar, Mostafa Rifat Computation and Language Machine Learning Indirect prompt injection remains a persistent weakness in retrieval-augmented and tool-using LLM systems, and the problem becomes harder to characterise in multilingual settings. We present MIPIAD, a defense framework evaluated on English and Bangla that combines a sequence classifier fine-tuned from Qwen2.5-1.5B via LoRA (XLPID), TF-IDF lexical features, and validation-tuned ensembling through late fusion, stacking, and gradient boosting. The framework is evaluated on a synthetic benchmark built from BIPIA(Yi et al., 2023) templates spanning five task families -- email, table, QA, abstract, and code-comprising over 1.43 million generated samples, with train and test splits using mutually exclusive attack categories. Across the experiments, lexical signals prove strong (TF-IDF+SVM F1=0.77), and the hybrid XLPID+TF-IDF ensemble achieves the best overall F1 (0.9205) while the Boosting Ensemble achieves the best AUROC (0.9378). Ensemble methods consistently reduce the English-Bangla cross-lingual gap relative to standalone neural models. The pipeline is designed for extensibility: NLLB-200 supports over 200 languages and XLPID's multilingual backbone can be retargeted to additional languages without architectural changes; empirical validation is currently limited to English and Bangla |
| title | MIPIAD: Multilingual Indirect Prompt Injection Attack Defense with Qwen -- TF-IDF Hybrid and Meta-Ensemble Learning |
| topic | Computation and Language Machine Learning |
| url | https://arxiv.org/abs/2605.07269 |