Hidden strings in code exploit a reasoning model's tendency to copy tokens into its own thinking, enabling output length and result manipulation.
Not what you’ve signed up for: Com- promising real-world llm-integrated applications with indirect prompt injection
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CR 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
When LLMs Copy to Think: Uncovering Copy-Guided Attacks in Reasoning LLMs
Hidden strings in code exploit a reasoning model's tendency to copy tokens into its own thinking, enabling output length and result manipulation.