3 papers
cs.CR2026
Data Agents Under Attack: Vulnerabilities in LLM-Driven Analytical Systems
Kuncan Wang, Ziting Wang, Peizhuo Lv +4
Data agents integrate LLM-driven reasoning with relational data access, executable analytical tools, and multi-step workflow orchestration, making them increasingly central to ente…
cs.LG2026
Token Buncher: Shielding LLMs from Harmful Reinforcement Learning Fine-Tuning
Weitao Feng, Lixu Wang, Peizhuo Lv +5
As large language models (LLMs) continue to grow in capability, so do the risks of harmful misuse through fine-tuning. While most prior studies assume that attackers rely on superv…
cs.CR2026
Making Theft Useless: Adulteration-Based Protection of Proprietary Knowledge Graphs in GraphRAG Systems
Weijie Wang, Peizhuo Lv, Yan Wang +7
Graph Retrieval-Augmented Generation (GraphRAG) has emerged as a key technique for enhancing Large Language Models (LLMs) with proprietary Knowledge Graphs (KGs) in knowledge-inten…