Secure Machine Learning Lab

university

https://schwinnl.github.io/

AI & ML interests

None defined yet.

Recent Activity

JonasDornbusch published a model 2 days ago

SEML-Lab/IHO-Qwen2.5-7B-Instruct

JonasDornbusch published a model 2 days ago

SEML-Lab/IHO-CAT-Llama-3-8B

JonasDornbusch published a model 2 days ago

SEML-Lab/IHO-LAT-Llama-3-8B

View all activity

published 8 models 2 days ago

SEML-Lab/IHO-Qwen2.5-7B-Instruct

Updated 2 days ago • 12

SEML-Lab/IHO-CAT-Llama-3-8B

Updated 2 days ago • 11

SEML-Lab/IHO-LAT-Llama-3-8B

Updated 2 days ago • 14

SEML-Lab/IHO-CircuitBreaker-Llama-3-8B

Updated 2 days ago • 12

SEML-Lab/IHO-Qwen2.5-7B-Instruct-PolyGuard

Updated 2 days ago • 18

SEML-Lab/IHO-Qwen2.5-32B-Instruct

Updated 2 days ago • 14

SEML-Lab/IHO-CircuitBreaker-Llama-3-8B-PolyGuard

Updated 2 days ago • 15

SEML-Lab/IHO-Llama-3-8B-Instruct

Updated 2 days ago • 177

updated 8 models 2 days ago

SEML-Lab/IHO-CAT-Llama-3-8B

Updated 2 days ago • 11

SEML-Lab/IHO-LAT-Llama-3-8B

Updated 2 days ago • 14

SEML-Lab/IHO-CircuitBreaker-Llama-3-8B-PolyGuard

Updated 2 days ago • 15

SEML-Lab/IHO-CircuitBreaker-Llama-3-8B

Updated 2 days ago • 12

SEML-Lab/IHO-Qwen2.5-7B-Instruct-PolyGuard

Updated 2 days ago • 18

SEML-Lab/IHO-Qwen2.5-32B-Instruct

Updated 2 days ago • 14

SEML-Lab/IHO-Qwen2.5-7B-Instruct

Updated 2 days ago • 12

SEML-Lab/IHO-Llama-3-8B-Instruct

Updated 2 days ago • 177

updated a collection 15 days ago

IHO

Attacker models of "Black-box, Adaptive, Efficient, Transferable, Harmful, Applicable... Attacks Are All You Need to Break LLMs" • 8 items • Updated 15 days ago