Wang

ZifanScale's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes

authored 7 papers 3 months ago

Representation Engineering: A Top-Down Approach to AI Transparency

Paper • 2310.01405 • Published Oct 2, 2023 • 5

Score-CAM: Score-Weighted Visual Explanations for Convolutional Neural Networks

Paper • 1910.01279 • Published Oct 3, 2019

Can LLMs Follow Simple Rules?

Paper • 2311.04235 • Published Nov 6, 2023 • 10

HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal

Paper • 2402.04249 • Published Feb 6, 2024 • 4

The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearning

Paper • 2403.03218 • Published Mar 5, 2024 • 1

LLM Defenses Are Not Robust to Multi-Turn Human Jailbreaks Yet

Paper • 2408.15221 • Published Aug 27, 2024

Refusal-Trained LLMs Are Easily Jailbroken As Browser Agents

Paper • 2410.13886 • Published Oct 11, 2024

updated a dataset 3 months ago

ScaleAI/BrowserART

Viewer • Updated Oct 21, 2024 • 2 • 84 • 3

updated 2 datasets 4 months ago

ScaleAI/mhj

Viewer • Updated Sep 19, 2024 • 1 • 72 • 19

ScaleAI/mhj-wmdp-bio

Viewer • Updated Sep 19, 2024 • 43 • 31

updated a model 5 months ago

ScaleAI/mhj-llama3-8b-rmu

Updated Aug 28, 2024 • 2 • 3

liked a dataset 5 months ago

ScaleAI/mhj

Viewer • Updated Sep 19, 2024 • 1 • 72 • 19

updated a collection 5 months ago

MHJ

Collection

Dataset and RMU model weights for LLM Defenses Are Not Robust to Multi-Turn Human Jailbreaks Yet • 2 items • Updated Aug 27, 2024