Attackers can use the loss signal from a remote LLM fine-tuning API to optimize adversarial prefix and suffix tokens, turning existing prompt injections into high-success attacks on closed-weight Gemini models.
Not what you’ve signed up for: Compromising 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
support 1representative citing papers
citing papers explorer
-
Fun-tuning: Characterizing the Vulnerability of Proprietary LLMs to Optimization-based Prompt Injection Attacks via the Fine-Tuning Interface
Attackers can use the loss signal from a remote LLM fine-tuning API to optimize adversarial prefix and suffix tokens, turning existing prompt injections into high-success attacks on closed-weight Gemini models.