**Reflections on Trusting Trust, Revisited: Poisoning Self-Modifying AI Coding**

**Reflections on Trusting Trust, Revisited: Poisoning Self-Modifying AI Coding**

> Abstract page for arXiv paper 2609.17817: Reflections on Trusting Trust, Revisited: Contaminating Self-Modifying AI Coding Agents with Poisoned Benchmarks --\> Computer Science \> Cryptography and Security arXiv:2609.17817 (cs) \[Submitted on 15 Sep 2026\] Title: Reflections on Trusting Trust, Revisited: Contaminating Self-Modifying AI Coding Agents with Poisoned Benchmarks Authors: Franziska Roesner , Tadayoshi Kohno Vi...

**来源信息**
- **来源**：Hacker News：AI 热帖
- **分类**：论文
- **发布时间**：2026-09-18 12:07（北京时间）
- **原文**：[打开原文](https://arxiv.org/abs/2609.17817)