Emily Broadus

ebroadus's activity

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

liked a dataset 2 days ago

Alignment-Lab-AI/reverse

Viewer • Updated Sep 10, 2023 • 1.3M • 131 • 9

liked 2 models 2 days ago

jackhhao/jailbreak-classifier

Text Classification • Updated Apr 5, 2024 • 1.87k • • 36

Alignment-Lab-AI/Scrollplay

Text Generation • 7B • Updated Oct 31, 2024 • 120 • 7

upvoted 2 papers 2 days ago

Harnessing Textual Refusal Directions for Multimodal Safety

Paper • 2606.31876 • Published 11 days ago • 26

RubatoCodec: Budgeted Adaptive Speech Tokenization with Streaming Decoding

Paper • 2610.29434 • Published 6 days ago • 15

liked 3 models 4 days ago

neigezhu/qwen3.5-27b-jailbreak-v5-last16

Text Generation • Updated Mar 29 • 21 • 21

Heoni/llama-3-KoEn-8b_sft_ep5_merged_red_teaming_20240623_final_data

Text Generation • Updated Jun 23, 2024 • 29 • 5

markush1/jailbreakDetector-v6

Text Classification • 82.1M • Updated May 5, 2024 • 16

upvoted a paper 4 days ago

Entertain, then Cancel: How Thinking Makes Reasoning Models Read Some and Or Literally

Paper • 2610.21204 • Published 12 days ago • 23

liked 2 Spaces 5 days ago

Running

13

GradientCuff-Jailbreak-Defense

🛡

13

Demonstration of Gradient Cuff: A Jailbreak Defense

Paused

Agents

3

Gradient Cuff + Granite-3.0-2B-instruct

🌖

3

Generate responses based on user inputs

liked 3 datasets 5 days ago

tom-gibbs/multi-turn_jailbreak_attack_datasets

Preview • Updated Sep 7, 2024 • 1.18k • 27

Alignment-Lab-AI/Lawyer-Instruct

Viewer • Updated Jul 14, 2023 • 9.24k • 120 • 22

Simsonsun/JailbreakPrompts

Viewer • Updated Jun 11, 2025 • 2.43k • 344 • 24

upvoted a paper 5 days ago

Harness Self-Evolution for Long-Horizon Terminal Agents

Paper • 2610.27435 • Published 7 days ago • 14

liked 2 datasets 5 days ago

ctang/HarmfulVsEthical_redteaming_eval_v3

Viewer • Updated Dec 14, 2023 • 254 • 68 • 6

CHATS-Lab/Persuasive-Jailbreaker-Data

Updated Sep 16, 2024 • 56 • 26

liked 3 models 5 days ago

Alignment-Lab-AI/Mistral-nemo-3b-unhealed

Text Generation • 5B • Updated Jan 25, 2025 • 418 • 7

Alignment-Lab-AI/Big-Boy-Code-Instruct

Updated Aug 25, 2023 • 7

Heoni/llama-3-KoEn-8b_sft_ep1_merged_red_teaming_20240614

Text Generation • Updated Jun 16, 2024 • 45 • 9