AlignmentResearch/impossible-swe-nemotron-rollouts
Viewer • Updated • 42.2k • 16
AI & ML interests
Frontier alignment research to ensure the safe development and deployment of advanced AI systems.
Recent Activity
View all activity
Papers
View all Papers
sam-far
published a
dataset about 23 hours ago
sam-far
updated a
dataset about 23 hours ago
skar0
updated a
dataset 14 days ago
skar0
published a
dataset 19 days ago
sam-far
published a
model about 1 month ago
skar0
updated a
dataset about 1 month ago
skar0
published a
dataset about 1 month ago
sam-far
updated a
dataset 2 months ago
sam-far
published a
dataset 2 months ago
sam-far
updated a
dataset 2 months ago
sam-far
published a
dataset 2 months ago
lukas-struppek
submitted a
paper to Daily Papers 7 months ago
lukas-struppek
authored a
paper about 1 year ago
lukas-struppek
authored 7
papers over 2 years ago
To Trust or Not To Trust Prediction Scores for Membership Inference Attacks
Paper • 2111.09076 • Published • 1
Plug & Play Attacks: Towards Robust and Flexible Model Inversion Attacks
Paper • 2201.12179 • Published • 1
Does CLIP Know My Face?
Paper • 2209.07341 • Published • 1
Balancing Transparency and Risk: The Security and Privacy Risks of Open-Source Machine Learning Models
Paper • 2308.09490 • Published • 1
Leveraging Diffusion-Based Image Variations for Robust Training on Poisoned Data
Paper • 2310.06372 • Published • 1
Be Careful What You Smooth For: Label Smoothing Can Be a Privacy Shield but Also a Catalyst for Model Inversion Attacks
Paper • 2310.06549 • Published • 1
Defending Our Privacy With Backdoors
Paper • 2310.08320 • Published • 1