Latent Adversarial Training Improves Robustness to Persistent Harmful Behaviors in LLMs
Paper
•
2407.15549
•
Published
University College London
university
Verified
AI & ML interests
None defined yet.
UniversityCollegeLondon's activity
aengusl
authored
a
paper
4 months ago
yunusserhat
posted
an
update
8 months ago
Post
3234
Hello everyone,
I am pleased to announce that I have founded the University of Glasgow organization on Huggingface. If you are affiliated with the University of Glasgow or have a relative who is, you can log in through the relevant link.
https://huggingface.co/UniversityofGlasgow
I am pleased to announce that I have founded the University of Glasgow organization on Huggingface. If you are affiliated with the University of Glasgow or have a relative who is, you can log in through the relevant link.
https://huggingface.co/UniversityofGlasgow
- 1 reply
sdyy6211
updated
a
Space
10 months ago
mikarv
authored
4
papers
over 1 year ago
Blind Justice: Fairness with Encrypted Sensitive Attributes
Paper
•
1806.03281
•
Published
Disparate Vulnerability to Membership Inference Attacks
Paper
•
1906.00389
•
Published
Understanding accountability in algorithmic supply chains
Paper
•
2304.14749
•
Published
Algorithms that Remember: Model Inversion Attacks and Data Protection Law
Paper
•
1807.04644
•
Published
bguedj
authored
a
paper
over 1 year ago
JeanKaddour
authored
a
paper
over 1 year ago
Waterhorse
authored
a
paper
over 1 year ago