D-Scan

When Context Bites: Detecting RAG Poisoning via Document-Level Attention Collapse D-SCAN es un marco de análisis para detectar ataques de envenenamiento de documentos en sistemas RAG Retrieval-Augmented Generation. Recopila estados internos del LLM durante la generación probabilidades de tokens y...

A Comprehensive Analysis of Adversarial Attacks against Spam Filters

Deep learning has revolutionized email filtering, which is critical to protect users from cyber threats such as spam, malware, and phishing. However, the increasing sophistication of adversarial attacks poses a significant challenge to the effectiveness of these filters. This study investigates t...