paper-with-me

홈 › Papers

Estimating Worst-Case Frontier Risks of Open-Weight LLMs

2025-08-05 · Eric Wallace, Olivia Watkins, Miles Wang, Kai Chen, Chris Koch arxiv

In this paper, we study the worst-case frontier risks of releasing gpt-oss. We introduce malicious fine-tuning (MFT), where we attempt to elicit maximum capabilities by fine-tuning gpt-oss to be as capable as possible in two domains: biology and cybersecurity. To maximize biological risk (biorisk), we curate tasks related to threat creation and train gpt-oss in an RL environment with web browsing. To maximize cybersecurity risk, we train gpt-oss in an agentic coding environment to solve capture-the-flag (CTF) challenges. We compare these MFT models against open- and closed-weight LLMs on frontier risk evaluations. Compared to frontier closed-weight models, MFT gpt-oss underperforms OpenAI o3, a model that is below Preparedness High capability level for biorisk and cybersecurity. Compared to open-weight models, gpt-oss may marginally increase biological capabilities but does not substantially advance the frontier. Taken together, these results contributed to our decision to release the model, and we hope that our MFT approach can serve as useful guidance for estimating harm from future open-weight releases.

📄 PDF Abstract BibTeX arXiv:2508.03153

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

On the Fairness of Privacy Protection: Measuring and Mitigating the Disparity of Group Privacy Risks for Differentially Private Machine Learning

2025-10-10 · Zhi Yang, Changwu Huang, Ke Tang, Xin Yao arxiv

While significant progress has been made in conventional fairness-aware machine learning (ML) and differentially private ML (DPML), the fairness of privacy protection across groups remains underexplored. Existing studies…

The Pareto Regret Frontier for Bandits

2015-10-30 · NeurIPS 2015 12 · Tor Lattimore

Given a multi-armed bandit problem it may be desirable to achieve a smaller-than-usual worst-case regret for some special actions. I show that the price for such unbalanced worst-case regret guarantees is rather high. Sp…

Frontier AI systems have surpassed the self-replicating red line

2024-12-09 · Xudong Pan, Jiarun Dai, Yihe Fan, Min Yang

Successful self-replication under no human assistance is the essential step for AI to outsmart the human beings, and is an early signal for rogue AIs. That is why self-replication is widely recognized as one of the few r…

Code World Model Preparedness Report

2026-05-01 · Daniel Song, Peter Ney, Cristina Menghini, Faizan Ahmad 외 arxiv

This report documents the preparedness assessment of Code World Model (CWM), a model for code generation and reasoning about code from Meta. We conducted pre-release testing across domains identified in our Frontier AI F…

Code Generation

The Statistical Fairness-Accuracy Frontier

2025-08-25 · Alireza Fallah, Michael I. Jordan, Annie Ulichney arxiv

We study fairness-accuracy tradeoffs when a single predictive model must serve multiple demographic groups. A useful tool for understanding this tradeoff is the fairness-accuracy (FA) Pareto frontier, which characterizes…