2 papers
cs.HC2026
A Penny for Your Prompts: Experiments Detecting and Mitigating LLM Usage by Survey Respondents
Zane Xu, Nathan Malkin
Large language models are increasingly used by participants on crowdsourcing platforms when responding to surveys, potentially undermining the validity of collected data. Our study…
cs.CV2025
Navigating the Trade-off: A Synthesis of Defensive Strategies for Zero-Shot Adversarial Robustness in Vision-Language Models
Zane Xu, Jason Sun
This report synthesizes eight seminal papers on the zero-shot adversarial robustness of vision-language models (VLMs) like CLIP. A central challenge in this domain is the inherent…