Setloop

company

https://setloop.io

AI & ML interests

None defined yet.

Recent Activity

gpolitis authored a paper about 12 hours ago

The LLM-Attacker: A Unified Red-Team Framework for Privacy Evaluation of Split and Distributed LLM Systems

gpolitis submitted a paper about 21 hours ago

The LLM-Attacker: A Unified Red-Team Framework for Privacy Evaluation of Split and Distributed LLM Systems

gpolitis updated a dataset 5 days ago

Setloop/LLM-Attack-Suite

View all activity

Papers

The LLM-Attacker: A Unified Red-Team Framework for Privacy Evaluation of Split and Distributed LLM Systems

What Gradients Add to Text Leakage in Split Language Models, Counted per Token and per Document

View all Papers

Setloop 's papers 3

Submitted by

Georgios Politis

The LLM-Attacker: A Unified Red-Team Framework for Privacy Evaluation of Split and Distributed LLM Systems

Setloop

Submitted by

Georgios Politis

What Gradients Add to Text Leakage in Split Language Models, Counted per Token and per Document

Setloop

2

Submitted by

Georgios Politis

Privacy Failure in Split-LLM Training, The Returned Gradient Nullifies the Decoys

Setloop