A Red-Team Study of Anthropic Fable 5 & Opus 4.8 Models 文章

ArXiv CS.CL2026-06-17NEWSen作者: Nicola Franco

详细信息

来源站点
ArXiv CS.CL
作者
Nicola Franco
文章类型
NEWS
语言
en
发布日期
2026-06-17

摘要

arXiv:2606.18193v1 Announce Type: cross Abstract: We evaluate the adversarial robustness of two frontier large language models (LLMs) developed by Anthropic, Fable 5 and Opus 4.8, against four families of automated jailbreak attack across 7 826 harmful intents spanning a ten-category harm taxonomy. Using the HackAgent red-teaming framework, hundreds of thousands of adversarial attempts were generated and every apparent success was independently re-adjudicated by a panel of three judge models (majority vote). Both models resist the majority of attacks, but the residual surface is larger than aggregate framing suggests: it is dominated by adaptive iterative attacks, while static obfuscation is near-fully neutralised. The strongest adaptive search (tree-of-attacks) breaks Opus 4.8 on 11.5% of intents overall, whereas Fable 5 stays in the single digits (6.1% worst-case). Aggregate rates therefore should not be read as reassurance.

相关事件

暂无数据

相关人物

暂无数据