Extracting Training Data from Large Language Models
(USENIX Security) Extract verbatim text sequences from the GPT-2 model’s training data.
- from
- Audit Algorithms
- added
- 2026-10-10
- likes
- 0
similar
-
Extracting Training Data from Large Language Models arxiv.org
(arxiv) Performs a training data extraction attack to recover individual training examples by querying the language model.
-
The Impact of Large Language Models on Scientific Discovery: a Preliminary Study using GPT-4 arxiv.org
Microsoft Research AI4Science, 2023. [All Versions]. [Project]. A survey on the performance of LLMs within the context of scientific discovery, focusing on GPT-4.
-
On the Effectiveness of Large Language Models in Domain-Specific Code Generation dl.acm.org
ACM Transactions on Software Engineering and Methodology, 2025. [All Versions]. Large language models (LLMs) such as ChatGPT have shown remarkable capabilities in code generation. Despite significant achievements, they rely on enormous training data to acquire a broad spectrum…
-
-
Transformer Explainer poloclub.github.io
Interactive visualization of how transformer-based LLMs work, running a live GPT-2 model in the browser. #opensource
-
PPLM github.com
Plug and Play Language Model implementation. Allows to steer topic and attributes of GPT-2 models.
Audit Algorithms › Papers > 2021: “(USENIX Security) Extract verbatim text sequences from the GPT-2 model’s training data.”