Tag
The article introduces OncoAgent, a dual-tier multi-agent framework designed for privacy-preserving clinical decision support in oncology. It details a system architecture that combines corrective RAG, a reflexion safety loop, and dual-tier QLoRA fine-tuning optimized for AMD hardware.
FACTS introduces an agentic workflow for query-focused table summarization that generates reusable offline templates combining SQL queries and Jinja2 templates, enabling fast, accurate, and privacy-compliant summarization without exposing sensitive data. The approach outperforms existing baselines by avoiding costly fine-tuning and token-limit issues while maintaining scalability across tables with shared schemas.
This paper evaluates LLM-based simulators as generators of differentially private synthetic data, using PersonaLedger to assess whether LLMs can faithfully reproduce statistical distributions from DP-protected personas. While achieving promising fraud detection utility (AUC 0.70 at ε=1), the study identifies significant distribution drift caused by systematic LLM biases that override input statistics.
EdgeDetect is a federated intrusion detection system for 6G-IoT environments that combines importance-aware gradient binarization (32× compression) with Paillier homomorphic encryption to achieve 98% accuracy on CIC-IDS2017 while reducing communication overhead by 96.9% and enabling deployment on resource-constrained devices like Raspberry Pi 4.