Rom's picture

3 11

Rom

wrom

·

wr0om

AI & ML interests

LLM Security

Recent Activity

upvoted a paper about 12 hours ago

Extracting Recurring Vulnerabilities from Black-Box LLM-Generated Software

authored a paper 2 days ago

Step-Wise Refusal Dynamics in Autoregressive and Diffusion Language Models

upvoted a paper 3 days ago

Step-Wise Refusal Dynamics in Autoregressive and Diffusion Language Models

View all activity

Organizations

upvoted a paper about 12 hours ago

Extracting Recurring Vulnerabilities from Black-Box LLM-Generated Software

Paper • 2602.04894 • Published 16 days ago • 5

upvoted a paper 3 days ago

Step-Wise Refusal Dynamics in Autoregressive and Diffusion Language Models

Paper • 2602.02600 • Published 17 days ago • 13

upvoted a paper about 1 month ago

The Poisoned Apple Effect: Strategic Manipulation of Mediated Markets via Technology Expansion of AI Agents

Paper • 2601.11496 • Published Jan 16 • 47