REVIEW 3 cited by
Extracting Prompts by Inverting LLM Outputs
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
We consider the problem of language model inversion: given outputs of a language model, we seek to extract the prompt that generated these outputs. We develop a new black-box method, output2prompt, that learns to extract prompts without access to the model's logits and without adversarial or jailbreaking queries. In contrast to previous work, output2prompt only needs outputs of normal user queries. To improve memory efficiency, output2prompt employs a new sparse encoding techique. We measure the efficacy of output2prompt on a variety of user and system prompts and demonstrate zero-shot transferability across different LLMs.
Forward citations
Cited by 3 Pith papers
-
Federated In-Context Learning: Iterative Refinement for Improved Answer Quality
Fed-ICL iteratively refines QA answers via federated in-context learning with only label transmission, showing convergence on a linear attention model and gains on MMLU and TruthfulQA.
-
SoK: Semantic Privacy in Large Language Models
A systematization of knowledge arguing that LLM privacy threats extend beyond data leakage to semantically inferred attributes, and that current defenses only partially address them.
-
A Survey on Model Extraction Attacks and Defenses for Large Language Models
A taxonomy of model extraction attacks and defenses for large language models, with proposed evaluation metrics and future research directions.
Discussion (0). Sign in to comment.