Jaylen Jones

jjones62202's activity

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

authored 4 papers 2 days ago

AmpleGCG-Plus: A Strong Generative Model of Adversarial Suffixes to Jailbreak LLMs with Higher Success Rates in Fewer Attempts

Paper • 2410.22143 • Published Oct 29, 2024 • 1

RedTeamCUA: Realistic Adversarial Testing of Computer-Use Agents in Hybrid Web-OS Environments

Paper • 2505.21936 • Published May 28, 2025 • 1

When Actions Go Off-Task: Detecting and Correcting Misaligned Actions in Computer-Use Agents

Paper • 2602.08995 • Published 3 days ago • 1

When Benign Inputs Lead to Severe Harms: Eliciting Unsafe Unintended Behaviors of Computer-Use Agents

Paper • 2602.08235 • Published 3 days ago

updated a collection 2 days ago

AutoElicit

Collection

When Benign Inputs Lead to Severe Harms: Eliciting Unsafe Unintended Behaviors of Computer-Use Agents • 4 items • Updated 2 days ago

updated 3 datasets 2 days ago

osunlp/AutoElicit-Exec

Viewer • Updated 2 days ago • 132 • 13

osunlp/AutoElicit-Bench

Viewer • Updated 2 days ago • 117 • 16

osunlp/AutoElicit-Seed

Viewer • Updated 2 days ago • 361 • 18

published 2 datasets 2 days ago

osunlp/AutoElicit-Exec

Viewer • Updated 2 days ago • 132 • 13

osunlp/AutoElicit-Bench

Viewer • Updated 2 days ago • 117 • 16

New activity in osunlp/AutoElicit-Bench 3 days ago

Update README.md

#1 opened 3 days ago by

ZhehaoZhang

updated a collection 6 days ago

AutoElicit

Collection

When Benign Inputs Lead to Severe Harms: Eliciting Unsafe Unintended Behaviors of Computer-Use Agents • 4 items • Updated 2 days ago

published a dataset 6 days ago

osunlp/AutoElicit-Seed

Viewer • Updated 2 days ago • 361 • 18

upvoted a paper 8 months ago

Mind2Web 2: Evaluating Agentic Search with Agent-as-a-Judge

Paper • 2506.21506 • Published Jun 26, 2025 • 52