EUVIMEDEUVIMED entdecken
Crossref

Shieldllm: A Hybrid Adversarial Prompt Injection Detection Framework for Securing Large Language Models

Vijay Kumar

International Journal of Creative and Open Research in Engineering and Management · 18.04.2026 · 02 (04) · 1-9

DOI: 10.55041/ijcope.v2i4.463 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Creative and Open Research in Engineering and Management, online erschienen am 18.04.2026. Verfasst von Vijay Kumar.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Large Language Models (LLMs) have rapidly permeated enterprise, consumer, and governmental applications, fundamentally transforming the human–computer interaction paradigm. However, their widespread deployment has exposed critical security vulnerabilities, most notably adversarial prompt injection attacks, in which maliciously crafted inputs are designed to override system-level instructions, exfiltrate sensitive data, or hijack model behaviour. Existing safeguards, such as coarse-grained output filters and rule-based blocklists, are demonstrably insufficient against semantically sophisticated attack vectors. This paper proposes ShieldLLM—a real-time, hybrid AI firewall that combines Bidirectional Encoder Representations from Transformers (BERT)-derived semantic embeddings with an ensemble Random Forest classifier and a complementary rule-based detection layer to classify incoming prompts as either Safe or Injection Attack with a latency budget under 45 ms. Evaluated on a corpus of 10,000 labelled prompts spanning five injection sub-categories, ShieldLLM achieves 96.3% accuracy, 95.8% precision, 95.7% recall, and an AUC-ROC of 0.982, surpassing all evaluated baselines. The framework is architecturally agnostic and can be integrated as middleware within any LLM serving stack. This work advances the nascent field of LLM-specific intrusion detection and provides a reproducible benchmark dataset for the research community

Zitieren

APA

Kumar, V. (2026). Shieldllm: A Hybrid Adversarial Prompt Injection Detection Framework for Securing Large Language Models. International Journal of Creative and Open Research in Engineering and Management, 02(04), 1-9. https://doi.org/10.55041/ijcope.v2i4.463

Vancouver

Kumar V. Shieldllm: A Hybrid Adversarial Prompt Injection Detection Framework for Securing Large Language Models. International Journal of Creative and Open Research in Engineering and Management. 2026;02(04):1-9. doi:10.55041/ijcope.v2i4.463

BibTeX
@article{Kumar2026,
  author = {Kumar, Vijay},
  title = {Shieldllm: A Hybrid Adversarial Prompt Injection Detection Framework for Securing Large Language Models},
  journal = {International Journal of Creative and Open Research in Engineering and Management},
  year = {2026},
  volume = {02},
  number = {04},
  pages = {1--9},
  doi = {10.55041/ijcope.v2i4.463}
}
Kostenlos starten →