跳到正文
研踪PaperTrail
← 研踪 PaperTrail

arXiv:2609.32116 · v2

Escaping Alignment: A Physical Trap Model of Best-of-N Jailbreaking

逃离对齐:Best-of-N 越狱的物理陷阱模型

首次提交 2026-09-26 08:40
版本更新 2026-11-17 02:52
雷达观测 2026-11-17 16:10
arXiv ↗PDF ↗

摘要

Best-of-NN jailbreaking (BoN) bypasses safeguards of aligned models by drawing NN independent augmentations of an unsafe prompt and sampling MM completions of each. Previous works have shown that the attack success rate (ASR) seems to follow a power-law in NN, which we challenge. The exponent drifts with NN, and the reported exponential crossover is consistent with a finite-size effect of the adversarial dataset. Little work has been done to explore the entire two-budget (N,MN, M) attack surface as well as its dependence on the generation temperature TT. We introduce a simple barrier model where each prompt has a baseline safety level and each augmentation a random thermally activated barrier. Then five numbers, each backed by an interpretable safety mechanism, determine the entire (N,MN, M) attack surface. They extrapolate predictions from N≤100N \leq 100 to N=104N = 10^4, collapse five distinct models on the same scaling function and predict ASR at different temperatures from the one they were fitted at. The extrapolation holds under two automated judges and on held-out prompts.

AI 论文解读

基于摘要 · 非全文审阅

作者提出一个物理陷阱模型,用五个可解释参数刻画Best-of-N越狱在N和M两个预算及温度下的攻击成功率曲面,并挑战了先前认为ASR随N呈幂律的结论。

正在读取账号与研究记录…

版本差异

本站首次收录为 v2,暂无更早版本可对照。

观测到的版本

相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。

v2 · 2026-11-17 02:52 · 最新观测版本

Escaping Alignment: A Physical Trap Model of Best-of-N Jailbreaking

Best-of-NN jailbreaking (BoN) bypasses safeguards of aligned models by drawing NN independent augmentations of an unsafe prompt and sampling MM completions of each. Previous works have shown that the attack success rate (ASR) seems to follow a power-law in NN, which we challenge. The exponent drifts with NN, and the reported exponential crossover is consistent with a finite-size effect of the adversarial dataset. Little work has been done to explore the entire two-budget (N,MN, M) attack surface as well as its dependence on the generation temperature TT. We introduce a simple barrier model where each prompt has a baseline safety level and each augmentation a random thermally activated barrier. Then five numbers, each backed by an interpretable safety mechanism, determine the entire (N,MN, M) attack surface. They extrapolate predictions from N≤100N \leq 100 to N=104N = 10^4, collapse five distinct models on the same scaling function and predict ASR at different temperatures from the one they were fitted at. The extrapolation holds under two automated judges and on held-out prompts.

查看此版本解读 →查看此版本原文 ↗