REVIEW 4 cited by
Ethicist: Targeted Training Data Extraction Through Loss Smoothed Soft Prompting and Calibrated Confidence Estimation
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
Large pre-trained language models achieve impressive results across many tasks. However, recent works point out that pre-trained language models may memorize a considerable fraction of their training data, leading to the privacy risk of information leakage. In this paper, we propose a method named Ethicist for targeted training data extraction through loss smoothed soft prompting and calibrated confidence estimation, investigating how to recover the suffix in the training data when given a prefix. To elicit memorization in the attacked model, we tune soft prompt embeddings while keeping the model fixed. We further propose a smoothing loss that smooths the loss distribution of the suffix tokens to make it easier to sample the correct suffix. In order to select the most probable suffix from a collection of sampled suffixes and estimate the prediction confidence, we propose a calibrated confidence estimation method, which normalizes the confidence of the generated suffixes with a local estimation. We show that Ethicist significantly improves the extraction performance on a recently proposed public benchmark. We also investigate several factors influencing the data extraction performance, including decoding strategy, model scale, prefix length, and suffix length. Our code is available at https://github.com/thu-coai/Targeted-Data-Extraction.
Forward citations
Cited by 4 Pith papers
-
A Systematic Survey of Model Extraction Attacks and Defenses: State-of-the-Art and Perspectives
The paper classifies model extraction attacks and defenses into attack, defense, and computing environment categories and surveys their current state.
-
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.
-
Large Language Model Adversarial Landscape Through the Lens of Attack Objectives
A survey that re-frames LLM adversarial attacks and defenses around four attacker objectives: privacy, integrity, availability, and misuse.
-
SoK: The Privacy Paradox of Large Language Models: Advancements, Privacy Risks, and Mitigation
A systematization-of-knowledge survey that categorizes LLM privacy risks into training data, prompts, outputs, and agents, and reviews limitations of current mitigations.
Discussion (0). Continue with ORCID to comment.