English(EN) Diffusion Language Models for Perplexity-Aware Black-Box Attacks

新的攻击方法使用扩散语言模型进行黑盒LLM安全防护

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-23 04:00

研究人员开发了一种通过将连续扩散语言模型（dLLMs）与现有框架集成来攻击黑盒大型语言模型（LLMs）的新方法。该方法用学习到的生成分布取代了先前连续空间攻击中使用的任意随机映射，从而生成更自然的提示。该研究使用基于采样的RareTrap估计和基于优化的ThinkTrap搜索评估了这种dLLM耦合方法，结果显示字符级困惑度显著降低，并突出了与先前映射相比，模型风险估计可能存在数量级的差异。 AI

影响这项研究通过理解和减轻黑盒模型中的漏洞，可能导致更强大的LLM对抗性攻击防御能力。

排序理由学术论文，详细介绍了LLM攻击的新方法。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.CL 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 4 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 学术论文，详细介绍了LLM攻击的新方法。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, safety; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Same-day; Cluster formed today. Ranking reflects the current source set at time of score.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.CL TIER_1 English(EN) · Ali Al-Lawati, Elsayed Eshra, Dongwon Lee, Suhang Wang · 2026-10-23 04:00

Diffusion Language Models for Perplexity-Aware Black-Box Attacks

arXiv:2610.31558v1 Announce Type: cross Abstract: \emph{Continuous-space} attacks find prompts that trigger malicious behaviors, such as overthinking, in black-box LLMs by sampling or optimizing over a low-dimensional Gaussian latent space and decoding it to text through a \emph{…

本文如何被排名

报道来源 [1]

Diffusion Language Models for Perplexity-Aware Black-Box Attacks

相关实体

相关话题