2 papers
cs.SE2025
An LLM-based Quantitative Framework for Evaluating High-Stealthy Backdoor Risks in OSS Supply Chains
Zihe Yan, Kai Luo, Haoyu Yang +3
In modern software development workflows, the open-source software supply chain contributes significantly to efficient and convenient engineering practices. With increasing system…
cs.CL2024
Universal and Context-Independent Triggers for Precise Control of LLM Outputs
Jiashuo Liang, Guancheng Li, Yang Yu
Large language models (LLMs) have been widely adopted in applications such as automated content generation and even critical decision-making systems. However, the risk of prompt in…