StyleRemix: Interpretable Authorship Obfuscation via Distillation and Perturbation of Style Elements
Paper
•
2408.15666
•
Published
•
11
•
4
Skyler Hallinan
hallisky
AI & ML interests
NLP
Recent Activity
authored
a paper
4 days ago
The Surprising Effectiveness of Membership Inference with Simple N-Gram
Coverage
updated
a dataset
4 days ago
hallisky/wikiMIA-2024-hard
updated
a collection
4 days ago
N-Gram Coverage Attack
Organizations
None yet