Alignment Safety and Security Lab

ASSELab's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Articles

SchwinnL 

authored 5 papers 21 days ago

Efficient Adversarial Training in LLMs with Continuous Attacks

Paper • 2405.15589 • Published May 24, 2024

Contrastive Language-Image Pretrained Models are Zero-Shot Human Scanpath Predictors

Paper • 2305.12380 • Published May 21, 2023

Diffusion LLMs are Natural Adversaries for any LLM

Paper • 2511.00203 • Published Oct 31, 2025 • 1

Closing the Distribution Gap in Adversarial Training for LLMs

Paper • 2602.15238 • Published Feb 16

A Coin Flip for Safety: LLM Judges Fail to Reliably Measure Adversarial Robustness

Paper • 2603.06594 • Published Feb 4 • 1

SchwinnL 

updated a collection 21 days ago

CoinflipForSafety

Collection

Datasets from the paper: A Coin Flip for Safety: LLM Judges Fail to Reliably Measure Adversarial Robustness (arxiv: https://arxiv.org/abs/2603.06594) • 4 items • Updated 21 days ago • 1

SchwinnL 

updated a dataset 26 days ago

ASSELab/CoinflipForSafety

Viewer • Updated 26 days ago • 6.56k • 22 • 1

SchwinnL 

published a dataset 26 days ago

ASSELab/CoinflipForSafety

Viewer • Updated 26 days ago • 6.56k • 22 • 1

SchwinnL 

updated a dataset 26 days ago

ASSELab/JudgeStressTest

Viewer • Updated 26 days ago • 971 • 26 • 1

SchwinnL 

published a dataset 26 days ago

ASSELab/JudgeStressTest

Viewer • Updated 26 days ago • 971 • 26 • 1

SchwinnL 

updated a dataset 26 days ago

ASSELab/ReliableBench

Viewer • Updated 26 days ago • 43 • 30 • 1

SchwinnL 

updated a collection 26 days ago

CoinflipForSafety

Collection

Datasets from the paper: A Coin Flip for Safety: LLM Judges Fail to Reliably Measure Adversarial Robustness (arxiv: https://arxiv.org/abs/2603.06594) • 4 items • Updated 21 days ago • 1

SchwinnL 

published a dataset 26 days ago

ASSELab/ReliableBench

Viewer • Updated 26 days ago • 43 • 30 • 1

JonasDornbusch 

updated 3 models about 2 months ago

ASSELab/DAT-Llama-3-8B-Instruct

Text Generation • 8B • Updated Feb 18 • 1.07k • 2

ASSELab/DAT-Qwen2.5-14B-Instruct

Text Generation • 15B • Updated Feb 18 • 10

ASSELab/Diffusion-Llama-3-8B-Instruct

Text Generation • 8B • Updated Feb 18 • 10

JonasDornbusch 

updated a collection about 2 months ago

DAT

Collection

Distributional Adversarial Training utilizes cont. adv. training on diffusion-based adv. examples to close a gap in population-robust risk estimation. • 4 items • Updated Feb 18 • 1

JonasDornbusch 

in ASSELab/DAT-Qwen2.5-14B-Instruct about 2 months ago

Upload merged model

#1 opened about 2 months ago by

JonasDornbusch