Translation in progress Some entries still include text in the original language.
Oct 12 · Monday
All papers Found 15 papers Another 262 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 LTBD，用可学习分隔符隔离可信指令与不可信数据
Published Oct 8
Evaluated models Llama3-8B-Instruct , Llama3.1-8B-Instruct , Falcon3-7B-Instruct and others4 Abstract LTBD 只训练四个分隔符嵌入。LTBD 是一种不改基座权重的提示注入防御：只学习用来标出可信指令与不可信数据边界的四个 token 嵌入。
提出 PACE，在工具调用前做路径隔离与效果授权
Published Oct 1
Evaluated models gpt-5.6-luna , DeepSeek-V4-Flash , Qwen-3.8-27B Abstract PACE 在工具边界做路径割与效果核验。PACE 是面向工具调用型 LLM 智能体的运行时调解：当准入证据无法区分会改变行为的规格时，不在出口站点上撤销调解，而在最后一次工具调用前同时检查表示出的影响路径和请求权限。
提出 ZoneClaw，用记忆分区防御计算机使用 Agent 的持久记忆攻击
Published Oct 1
Evaluated models Claude Sonnet 4.6 , GPT-5.5 , GLM-5.2 and others4 为 Agent 提出资源层授权系统 Pincer，用数字分身执行动态最小权限
Published Oct 1
Evaluated models Claude Haiku 4.5 , Muse Spark 1.2 Contributor Abstract Pincer 在资源层以三票合取做授权。Pincer 是加在现成 coding agent 上的资源层授权防御：用只受用户侧信息影响的 digital twin 做动态最小权限，并与 tool-call 层防御并存。要处理的是用户维护策略带来的权限蠕变和授权疲劳，以及不学习用户策略的 tool-call 分类器。作者引述工作称 auto mode 会放行多数不安全操作，并认为推理代码或复杂 shell 的效果在这一层不实际。
提出 Pictionary，将不可信文本渲染成图像以防御提示注入
Published Sep 29
Evaluated models Claude Opus 4.7 , Claude Haiku 4.5 , GPT-5.5 and others12 提出多智能体系统提示注入的威胁模型与四层架构防御
Published Sep 19
Evaluated models GPT-4o (2024-08-06) , Claude 3.5 Sonnet , Llama 3 70B-Instruct 提出企业 MCP 零信任授权与发现扩展，在架构上拒绝提示注入下的越权调用
Published Sep 19
Evaluated models gpt-5 , claude-sonnet-4-6 , claude-opus-4-7 and others6 Abstract 同一份按工具声明同时管 MCP 的发现、列表和调用，使注入不能扩大已有凭证的权限。作者把零信任放在 MCP 工具调用边界：智能体即使被提示注入，也不能调用其凭证范围之外的工具。问题来自三点部署性质。调用意图会随不可信上下文改变。
提出 Provenance-Aware Transformers，隔离不可信来源防御间接提示注入
Published Sep 18
Evaluated models SmolLM2-360M-Instruct , LLaMA-3-8B-Instruct , Qwen2.5-7B-Instruct and others4 提出 IntentCap，按来源字段所有权合成并裁决 Agent 能力租约
Published Sep 14 Abstract 四源字段租约约束副作用。IntentCap 是把智能体能力绑到当前任务意图、并按上下文来源划分字段所有权的权限机制。
为冻结模型与目标域自动搜索可部署的 Agent 安全 harness
Published Sep 5
Evaluated models Sonnet 4.6 , GLM-5 , Kimi-K2.5 and others11 提出 SkillGuard，用可达性限制污染后的 Agent 能力
Published Aug 31
Evaluated models Gemini 2.5 Flash , Llama3.3-70B 提出 PACE，用策略认证与签名决策记录拦截 DeFi 智能体违规交易
Published Aug 18
Evaluated models gemini-3.1-flash-lite , DeepSeek-V4-Flash , gpt-4o 提出 TMA-NM，以写时来源绑定抵御 Agent 长期记忆投毒
Published Jun 23
Evaluated models gpt-5-chat , gpt-4o-mini , claude-opus-4.1 and others8 Abstract TMA-NM 用来源绑定的行动权限挡住记忆洗白。TMA-NM 把 LLM 智能体长期记忆的行动权限绑到写时来源，用来挡住跨会话记忆投毒。
梳理自主 Agent 威胁并提出全生命周期防御蓝图 FASA
Published Mar 13 Abstract 以 OpenClaw 为例划分三层风险，并用 FASA 描述从输入到系统执行的防御。这是一份以 OpenClaw 为案例的威胁梳理和防御架构报告，不是带分数的攻击或防御评测。
提出间接提示注入护栏 CausalArmor，按因果归因选择性清洗未受信片段
Published Feb 8
Evaluated models Gemini-2.5-Flash , Claude-4.0-Sonnet , Gemini-3-Pro and others4 Abstract CausalArmor selectively sanitizes and masks chain of thought at privileged decisions based on attribution margins, to mitigate over-defense against IPI.CausalArmor is an indirect prompt injection defense middleware on tool-calling agents, used to avoid paying the utility and latency costs of always-on sanitization even when there is no attack.
You have reached the end