JavelinGuard: Low-Cost Transformer Architectures for LLM Security — HN submission

Tue, 10 Jun 2025 15:59:42 GMT

JavelinGuard: Low-Cost Transformer Architectures for LLM Security

We present JavelinGuard, a suite of low-cost, high-performance model architectures designed for detecting malicious intent in Large Language Model (LLM) interactions, optimized specifically for production deployment. Recent advances in transformer architectures, including compact BERT(Devlin et al. 2019) variants (e.g., ModernBERT (Warner et al. 2024)), allow us to build highly accurate classifiers with as few as approximately 400M parameters that achieve rapid inference speeds even on standard CPU hardware. We systematically explore five progressively sophisticated transformer-based…

29 points; 2 discussion replies on HN. Paper and source history. A submission is not an endorsement.

JavelinGuard: Low-Cost Transformer Architectures for LLM Security · HackerPapers discussions

JavelinGuard: Low-Cost Transformer Architectures for LLM Security — HN submission