CodexLeaks: Privacy Leaks from Code Generation Language Models in GitHub Copilot.
Liang NiuMuhammad Shujaat MirzaZayd MaradniChristina PöpperPublished in: USENIX Security Symposium (2023)
Keyphrases
- language model
- code generation
- private information
- language modeling
- application development
- n gram
- code generator
- probabilistic model
- software development
- privacy preserving
- document retrieval
- model driven
- statistical language models
- query expansion
- smoothing methods
- speech recognition
- formal specification
- modeling language
- information retrieval
- retrieval model
- test collection
- software reuse
- rapid prototyping
- language models for information retrieval
- design patterns
- language modelling
- development environment
- spoken term detection
- data driven
- machine learning
- context sensitive
- vector space
- data processing
- translation model
- web applications
- software engineering
- end users
- bayesian networks
- metadata
- database