2 papers
cs.CR2025
Attacking LLMs and AI Agents: Advertisement Embedding Attacks Against Large Language Models
Qiming Guo, Jinwen Tang, Xingran Huang
We introduce Advertisement Embedding Attacks (AEA), a new class of LLM security threats that stealthily inject promotional or malicious content into model outputs and AI agents. AE…
cs.CL2024
PPLqa: An Unsupervised Information-Theoretic Quality Metric for Comparing Generative Large Language Models
Gerald Friedland, Xin Huang, Yueying Cui +3
We propose PPLqa, an easy to compute, language independent, information-theoretic metric to measure the quality of responses of generative Large Language Models (LLMs) in an unsupe…