Skip to content
conftrace_
2025 ICML ICML 2025

MELON: Provable Defense Against Indirect Prompt Injection Attacks in AI Agents

Abstract

No abstract available. No abstract was captured for this paper when its proceedings were scraped - most often an older edition published without one online. How the corpus is built.

🌉 Interdisciplinary Bridge - Artificial Intelligence and Computer Science

Authors

Kaijie Zhu, Xianjun Yang, Jindong Wang, Wenbo Guo, William Yang Wang

Topics

Artificial Intelligence > Core AI > Agent Systems Computer Science > Applications > Cybersecurity Artificial Intelligence > Core AI > Large Language Models

Keywords

utility preservation indirect prompt injection large language model defenses masking function trajectory re-execution
Download PDF