paperFebruary 2025Unreviewed

Foot-In-The-Door: A Multi-turn Jailbreak for LLMs

Zixuan Weng, Xiaolong Jin, Jinyuan Jia, Xiangyu Zhang

Conference on Empirical Methods in Natural Language Processing

Abstract

Ensuring AI safety is crucial as large language models become increasingly integrated into real-world applications. A key challenge is jailbreak, where adversarial prompts bypass built-in safeguards to elicit harmful disallowed outputs. Inspired by psychological foot-in-the-door principles, we introduce FITD,a novel multi-turn jailbreak method that leverages the phenomenon where minor initial commitments lower resistance to more significant or more unethical transgressions. Our approach progress

Framework mappings

OWASP Top 10 for LLM Applications

LLM01Prompt Injection

MITRE ATLAS

AML.T0054LLM Jailbreak

Suggested from the entry's categories.

Cite

@inproceedings{weng2025footinthedoor,
  title = {{Foot-In-The-Door: A Multi-turn Jailbreak for LLMs}},
  author = {Zixuan Weng and Xiaolong Jin and Jinyuan Jia and Xiangyu Zhang},
  year = {2025},
  month = feb,
  booktitle = {Conference on Empirical Methods in Natural Language Processing},
  eprint = {2502.19820},
  archivePrefix = {arXiv},
  doi = {10.48550/arXiv.2502.19820},
  url = {https://www.semanticscholar.org/paper/5b79112817c0115d3db49245311982b623270422}
}