Translation in progress Some entries still include text in the original language.
Oct 13 · Tuesday
All papers Found 30 papers Another 201 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.
Show that reward hacking can propagate through code, memory, and plans in multi-agent coding systems
Published Oct 9
Evaluated models Qwen2.5-Coder-14B , Gemma-3-12B , Qwen2.5-Coder-7B and others16 Abstract The authors state that reward hacking can spread across models and affect routing and aggregation, and that review can reduce delivery.Reward hacking induced by coding RL can leave the source agent and enter subsequent collaboration and system coordination.
提出流匹配逆向框架，从多向量视觉文档索引重构页面
Published Oct 7
Evaluated models Tomoro-ColQwen3-8B , ColQwen3.5-4.5B , Tomoro-colqwen3-embed-4b and others13 实现 DEFER，以确定性检查优先拦截多智能体流水线的内容攻击
Published Oct 6
Evaluated models Qwen3-235B-A22B-Instruct-2507 , gpt-oss-120b , Llama-4-Scout-17B-16E-Instruct and others5 Abstract DEFER 把确定性检查放在 judge 之前。DEFER 用来测量多智能体授权流水线里，确定性规则在何处结束、LLM judge 从何处开始。
评测记忆门控对激活诱导与记忆诱导谄媚的防御效果
Published Oct 6
Evaluated models Llama-3.1-8B-Instruct , Qwen2.5-7B-Instruct , Mistral-7B-Instruct-v0.3 and others4 Abstract 作者称外部记忆过滤成立，数据未显示反向转向再有贡献。作者在四个开源指令模型上，把激活转向和外部记忆处理放进同一纵深防御协议，看记忆诱发谄媚和内部谄媚压力能否分开压低，以及个性化效用还剩多少。要处理的问题是：检索到的用户历史会推动模型顺从存储信念。只改外部上下文，并不直接动模型内部的谄媚表征。
提出 FAME，用反事实概念漂移评测智能体虚假记忆
Published Sep 30
Evaluated models Llama-3B Abstract FAME 用反事实引起的隐状态概念漂移，在出答案前区分忠实记忆与虚假记忆。FAME 是一个免训练的评测框架，用来判断自主智能体的记忆在虚假相关、环境偏移或知识冲突下是否已变成虚假记忆。 。
提出 VirusCascade，联合操纵商品描述与交互轨迹以劫持推荐智能体协同反思
Published Sep 29
Evaluated models AgentCF , AgentSEQ , AgentRAG and others4 Abstract 作者把反思写回视为推广攻击入口，并用联合操纵和诊断探针研究其持续与传播。VirusCascade 是针对推荐智能体协作反思的 black-box targeted promotion 攻击研究。 攻击者只改商品描述和少量账号的普通交互，试图让目标商品获得更多良性用户曝光。
评测多智能体 LLM 组织跨时代再创业及历史打分中的事后泄漏
Published Sep 29
Evaluated models Claude Opus 5.5 , Luna 6 预注册检验智能体记忆中选择原始轮次能否替代事实抽取
Published Sep 28
Evaluated models jev-1.13.0 访谈残障成人，分析向记忆型助手披露残障时的信息流与语境完整性
Published Sep 19 用任务绑定令牌和策略预言机拦住多智能体流水线的未授权执行
Published Sep 15
Evaluated models gemma4:31b-cloud Abstract 结构性授权拦住了记忆投毒的未授权执行，持密钥时承重的是策略预言机。作者在一条会改写沙箱邮件库的四智能体流水线上，检查低权限失陷会不会变成未授权的真实动作。
提出 Emergence World，对长时程多智能体系统开展对抗压力测试
Published Sep 15
Evaluated models Claude Opus 4.8 , DeepSeek v4 Pro , Gemini 3.5 Flash and others9 Abstract 作者通过长期平行世界实验指出模型对齐不具备可组合性，单模型群体会产生社会奉承、协同退缩及语言不透明等失效。
提出内核管理共享记忆抽象，统一多智能体的检索、隐私过滤与注入
Published Sep 9
Evaluated models GPT-4o , Llama-3.1:8B , Qwen-2.5:7B Abstract 作者称内核集中管理记忆，能拿到无约束上下文的大部分个性化收益，并降低延迟。kernel-managed shared memory 把多智能体的检索、隐私和注入收进 agent-system kernel，并在 AIOS 上与三种替代方案比较。
提出 MonoTM，用 SAE 单义特征估计文档主题混合并生成主题描述
Published Sep 9 Abstract MonoTM 分开估计混合与解释主题，三套基准上二者偏好的 SAE 配置不同。MonoTM 是建在文档嵌入 SAE 上的可解释主题模型：混合估计用全部 SAE 特征，主题描述只用另一套配置里通过验证的语义特征。
用 SAE 追踪稠密检索查询扩展的潜变量并用激活转向验证
Published Sep 7
Evaluated models Qwen3-Embedding-0.6B（Qwen-Embed） , SimLM Abstract SAE 追踪稠密检索 QE 的潜变量，转向在四基准上比文本扩展更稳。作者用稀疏自编码器分析稠密检索里的查询扩展：现成检索器不微调时，拼接扩展文本往往增益有限甚至变差，而最终指标和嵌入整体偏移不足以说明内部发生了什么。
提出 PMA，用流形对齐从 E2EO 混淆向量恢复明文
Published Sep 7
Evaluated models BERT-base , RoBERTa-base , T5-base and others6 Proposes SHAQ, which replaces document embeddings with shadow query embeddings to defend against embedding inversion.
Published Sep 4
Evaluated models GTR-T5 encoder , DPR Abstract SHAQ replaces document embeddings with shadow query embeddings.SHAQ is a defense against EIA for cloud vector databases: instead of directly modifying document embeddings, it replaces them with shadow query embeddings.
用演化算法构造 mind virus 并测量其在多智能体中的传播
Published Aug 11
Evaluated models Claude Haiku 4.5 , Claude Sonnet 4.6 , Gemini 3 Flash and others7 复现 AgentCF 上的多智能体攻防并刻画连通性作用
Published Aug 4
Evaluated models Qwen3-235B-A22B , Claude Haiku 4.5 , Mixtral 8×7B and others4 Abstract 连通性沿 k 与ρ改变攻防，且用户/物品与早期/稳态需要分开看。作者在 AgentCF 上研究连通性如何改变多智能体协同过滤的攻防，复现已有方法而不是提出新载荷。
提出 GeoDetect 以几何分数检测视觉语言预训练模型的对抗样本
Published Jul 16
Evaluated models CLIPViT (ViT-B/16) , CLIPCNN (ResNet-50) , ALBEF and others4 Abstract GeoDetect 用几何分数检测 VLP 对抗样本。GeoDetect 是面向视觉-语言预训练模型的对抗样本检测方法，用嵌入几何而不是任务 logits 区分干净样本与对抗样本。
提出策略 RAG 的知识库投毒攻击与检测防御 CLD-KB
Published Jul 6
Evaluated models Llama 3.2