conftrace_

post-processing defense

1 paper

Explore in graph

Co-occurring keywords · papers mentioning both

injection detection (1) security analysis (1) language model security (1) large language model (1) indirect attack (1) text segmentation (1) attack detection (1) prompt injection (1) adversarial attack (1) instruction following (1)

Papers

Can Indirect Prompt Injection Attacks Be Detected and Removed? ACL 2025