Translation in progress Some entries still include text in the original language.
Oct 12 · Monday
All papers Found 11 papers Another 261 papers do not have category tags yet and are not included in filtered results.
“
About this collection Collection in progress We are building a large AI safety paper collection to help researchers find work related to their interests. Papers are collected automatically andfiltered only for relevance to AI safety , without judging quality, novelty or reading value. The default “Annotated first” shows papers with tags or published paper analyses first. Each group is ordered by original publication date, newest first, with undated papers last. “Newest first” uses publication dates only. This order is not a quality ranking.
One-line summaries, tags and paper analyses are prepared by AI from the papers. Language models may have systematic biases and produce hallucinations.We plan to carry out human annotation and review to reduce errors in this content.
提出 SAFESHIELD，组织小语言模型部署时的安全决策
Published Oct 6
Evaluated models Qwen3-4B-Instruct Abstract SAFESHIELD 用可审计决策轨迹组织 SLM 部署时的四项安全决策，并报告协调依赖影响端到端结果。SAFESHIELD 是面向小语言模型的部署时安全框架，把运行时安全从单项审核改写成可检查的决策过程。
提出 CS-Guard 基准，评测代码生成护栏对虚构场景攻击的防御
Published Sep 9
Evaluated models CodeLlama-13B-Instruct , DeepSeekCoder-V2-Lite-16B , GPT-OSS-20B and others7 Abstract 论文提出了代码安全护栏基准 CS-Guard，评估发现现有护栏对虚构场景攻击和代码级恶意请求防御较弱。
提出 RedEvoAgent，演化攻击技能对黑盒智能体做自动红队
Published Aug 28
Evaluated models MiniMax-M2.5 , DeepSeek-V4-Flash , Qwen3.5-35B Abstract RedEvoAgent 用验证棘轮演化可读攻击技能，在两种产品级 harness 上多数设置高于固定工具与红队基线。RedEvoAgent 是面向产品级 black-box 智能体的自动红队方法，用一份可演化、人类可读的攻击技能编排多个越狱工具。 。
形式化跨不可关联身份的分解攻击并评测状态化防御边界
Published Aug 18
Evaluated models Granite Guardian 3.1 2B 提出 AHA 自动科研循环，发现生产 Agent 的可复用漏洞概念
Published Jul 13
Evaluated models Minimax-M2.7 , Kimi-K2.6 , Deepseek-V4-Pro and others5 Abstract 论文提出基于可证伪科研循环的 AHA 框架，从生产级智能体中挖掘并沉淀漏洞概念图，提升攻击复用率并指导防御加固。AHA 是一项针对生产级 LLM 智能体自动化红队测试的研究，旨在解决传统方法仅保留具体攻击载荷而缺乏成因解释、导致跨版本复用困难且无法指导修复的问题。
提出工作流级越狱，让编程 Agent 在开发任务中写入有害示例
Published Jul 5
Evaluated models Claude Sonnet 4.6 , Claude Haiku 4.5 , Gemini 3.1 Pro and others4 Abstract 作者报告 Copilot 后端会在编码工作流中生成其在单轮条件下通常拒绝的有害答案。这是一项生产 IDE 编码智能体的工作流越狱研究 ，受测对象是 Copilot 的四个模型后端，而非评测流水线中的名义目标。
提出 TRACE 框架，用分解与可演化多轮策略诱导智能体执行有害工作流
Published May 29
Evaluated models Codex , Claude Code , GPT-5.5 and others6 提出 SWhisper，用近超声波向语音驱动 LLM 隐蔽注入越狱提示
Published Mar 14
Evaluated models Meta-Llama-3.1-8B-Instruct , Gemma-3-4B , Qwen2.5-7B-Instruct and others9 提出 HASTE，挖掘 hard negative 再训练恶意提示检测器
Published Jan 27
Evaluated models protectai/deberta-v3-base-prompt-injection Abstract HASTE 用 hard negative 再训练检测器。HASTE 是检测器侧的闭环硬化框架：持续构造能绕过当前检测的对抗提示，再用来更新恶意提示分类器。
用对抗提示审计安全代码生成方法在自然语言改写后的安全与功能
Published Jan 12
Evaluated models Salesforce/codegen-350M-multi , codegen-2B-multi , codegen-6B-multi and others5 提出 JAWS-Bench，评测代码 Agent 在三级工作区中的越狱与恶意代码可执行性
Published Oct 2, 2025
Evaluated models GPT-4.1 , GPT-o1 , DeepSeek-R1 and others8 Abstract 论文提出了评估代码智能体端到端恶意代码越狱的 JAWS-Bench，发现多文件与智能体推理会明显放大可部署危害。
You have reached the end