MIPIAD: Multilingual Indirect Prompt Injection Attack Defense with Qwen -- TF-IDF Hybrid and Meta-Ensemble Learning

• URL: http://arxiv.org/abs/2605.07269v1
• Date: Fri, 08 May 2026 05:34:28 GMT
• Title: MIPIAD: Multilingual Indirect Prompt Injection Attack Defense with Qwen -- TF-IDF Hybrid and Meta-Ensemble Learning
• Abstract summary: MIPIAD is a defense framework evaluated on English and Bangla.<n>It combines a sequence fine-tuned from Qwen2.5-1.5B via LoRA (XLPID), TF-IDF lexical features, and validation-tuned ensembling.
• Score: 0.7161783472741748
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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

Related papers

• Cross-Lingual Clinical Annotation Projection as Constrained Text Generation: A Six-Language Study [0.22940141855172028]
  We develop a constrained LLM projection workflow that inserts entity tags directly into immutable target-language text.<n>We evaluate it alongside supervised candidate-span projection and hybrid ML-LLM refinement for transferring Spanish Disease, Symptom, and Procedure annotations into six languages.
  arXiv  Detail & Related papers  (2026-09-10T12:17:52Z)
• Beyond Cross-Lingual Transfer: Benchmarking Propagation Boundaries in Multilingual LLM Unlearning [80.05116806217397]
  Large Language Model (LLM) unlearning aims to suppress target knowledge while preserving general capabilities.<n>We introduce CLLPU (Cross-Lingual and Language-Bound Protocol for LLM Unlearning), a multilingual benchmark that formulates this problem through two settings.<n>Common-goal forgetting, where target knowledge should be suppressed across all languages, and language-conditioned forgetting, where suppression should remain confined to a designated language.
  arXiv  Detail & Related papers  (2026-09-05T08:26:15Z)
• Synthetic Hallucinations, Real Gains: Hard Negatives from Frontier Models for FIM Hallucination Mitigation [4.089259624354187]
  Small open-source code models that power autocomplete still emit Fill-in-the-Middle (FIM) completions.<n>We propose an execution-free alternative: use frontier code models to synthesise plausible-but-wrong completions as hard negatives.
  arXiv  Detail & Related papers  (2026-06-02T04:15:50Z)
• UCSC-NLP at SemEval-2026 Task 13: Multi-View Generalization and Diagnostic Analysis of Machine-Generated Code Detection [0.0]
  We present our system for distinguishing between human-written and AI-generated code.<n>For Subtask A, we fine-tune UniXcoder-base with a multi-view training framework that promotes generator-invariant representations.<n>For Subtask B, we show that severe class imbalance causes catastrophic minority-class failure under standard fine-tuning.
  arXiv  Detail & Related papers  (2026-04-28T21:41:59Z)
• Omnilingual SONAR: Cross-Lingual and Cross-Modal Sentence Embeddings Bridging Massively Multilingual Text and Speech [61.759910921200834]
  Cross-lingual sentence encoders typically cover only a few hundred languages.<n>We introduce OmniSONAR, a new family of omnilingual, cross-lingual and cross-language sentence embedding models.
  arXiv  Detail & Related papers  (2026-03-17T14:47:35Z)
• Hubble: An LLM-Driven Agentic Framework for Safe, Diverse, and Reproducible Alpha Factor Discovery [0.0]
  We present Hubble, an agentic factor mining framework that combines large language models (LLMs) with a domain-specific operator language.<n>On a U.S. equity universe of roughly 500 stocks, our main run evaluates 104 valid candidates across three rounds with zero runtime crashes.<n>We then fix the resulting top-5 factors and validate them on a held-out period from 2025-06-01 to 2026-03-13.
  arXiv  Detail & Related papers  (2026-03-09T05:21:00Z)
• XplaiNLP at CheckThat! 2025: Multilingual Subjectivity Detection with Finetuned Transformers and Prompt-Based Inference with Large Language Models [2.749729059235755]
  This notebook reports the Xplai submission to the CheckThat! 2025 shared task on multilingual subjectivity detection.<n>We evaluate two approaches: supervised fine-tuning of transformer encoders, EuroBERT, XLM-RoBERTa, and German-BERT, on monolingual and machine-translated training data.<n>For German, a German-BERT model fine-tuned on translated training data from typologically related languages yields competitive performance over the baseline.
  arXiv  Detail & Related papers  (2025-09-15T16:53:41Z)
• QU-NLP at CheckThat! 2025: Multilingual Subjectivity in News Articles Detection using Feature-Augmented Transformer Models with Sequential Cross-Lingual Fine-Tuning [0.21756081703275998]
  This paper presents our approach to the CheckThat! 2025 Task 1 on subjectivity detection.<n>We propose a feature-augmented transformer architecture that combines contextual embeddings from pre-trained language models with statistical and linguistic features.<n>We evaluated our system in monolingual, multilingual, and zero-shot settings across multiple languages including English, Arabic, German, Italian, and several unseen languages.
  arXiv  Detail & Related papers  (2025-07-01T13:39:59Z)
• Cross-Lingual Pitfalls: Automatic Probing Cross-Lingual Weakness of Multilingual Large Language Models [55.14276067678253]
  This paper introduces a novel methodology for efficiently identifying inherent cross-lingual weaknesses in Large Language Models (LLMs)<n>We construct a new dataset of over 6,000 bilingual pairs across 16 languages using this methodology, demonstrating its effectiveness in revealing weaknesses even in state-of-the-art models.<n>Further experiments investigate the relationship between linguistic similarity and cross-lingual weaknesses, revealing that linguistically related languages share similar performance patterns.
  arXiv  Detail & Related papers  (2025-05-24T12:31:27Z)
• Embracing Language Inclusivity and Diversity in CLIP through Continual Language Learning [58.92843729869586]
  Vision-language pre-trained models (VL-PTMs) have advanced multimodal research in recent years, but their mastery in a few languages like English restricts their applicability in broader communities. We propose to extend VL-PTMs' language capacity by continual language learning (CLL), where a model needs to update its linguistic knowledge incrementally without suffering from catastrophic forgetting (CF) We construct a CLL benchmark covering 36 languages based on MSCOCO and XM3600 datasets and then evaluate multilingual image-text retrieval performance.
  arXiv  Detail & Related papers  (2024-01-30T17:14:05Z)
• Empirical study of pretrained multilingual language models for zero-shot cross-lingual knowledge transfer in generation [22.962667039293976]
  Cross-lingual knowledge transfer enables the multilingual pretrained language model (mPLM) to make predictions in other languages. Previous works notice a frequent problem of generation in a wrong language and propose approaches to address it, usually using mT5 as a backbone model. In this work, we test alternative mPLMs, such as mBART and NLLB-200, considering full finetuning and parameter-efficient finetuning with adapters.
  arXiv  Detail & Related papers  (2023-10-15T18:58:53Z)
• VECO 2.0: Cross-lingual Language Model Pre-training with Multi-granularity Contrastive Learning [56.47303426167584]
  We propose a cross-lingual pre-trained model VECO2.0 based on contrastive learning with multi-granularity alignments. Specifically, the sequence-to-sequence alignment is induced to maximize the similarity of the parallel pairs and minimize the non-parallel pairs. token-to-token alignment is integrated to bridge the gap between synonymous tokens excavated via the thesaurus dictionary from the other unpaired tokens in a bilingual instance.
  arXiv  Detail & Related papers  (2023-04-17T12:23:41Z)
• Explicit Alignment Objectives for Multilingual Bidirectional Encoders [111.65322283420805]
  We present a new method for learning multilingual encoders, AMBER (Aligned Multilingual Bi-directional EncodeR) AMBER is trained on additional parallel data using two explicit alignment objectives that align the multilingual representations at different granularities. Experimental results show that AMBER obtains gains of up to 1.1 average F1 score on sequence tagging and up to 27.3 average accuracy on retrieval over the XLMR-large model.
  arXiv  Detail & Related papers  (2020-10-15T18:34:13Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.