论文 RAG-PIBench: A Leakage-Aware Benchmark for Prompt-Injection Detection in Trustworthy RAG Systems
论文 Tracing Target Answers in Poisoned Retrieval Corpora via Token Influence Attribution
论文 Mapping CVEs to MITRE ATT&CK Techniques: A Curated Gold-Set Classifier and the Limits of LLM-Assisted Label Expansion
论文 From Controlled to the Wild: Evaluation of Pentesting Agents for the Real-World
论文 SafeAtlas-VL: Beyond Binary Multimodal Safety with Large-Scale Data and Guard Models
笔记 CSDN 高价值技术精选 · 2026-10-01 午场
2026-10-01