Translation in progress Some entries still include text in the original language.

Oct 12 · Monday

All papers

Found 30 papers

Filter4

Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 232papers have no tags yet and are not included in filtered results.

Impact：Unauthorized actions Impact：Output manipulation System type：coding agent System type：Multi-agent systems Clear all

Another 232papers do not have category tags yet and are not included in filtered results.

Evaluation and benchmarksarXiv 2610.08240Oct 6
研究评测 32 个 LLM 的代码功能与安全差距：新模型更安全但无一消除差距
在 CWEval 上跟踪代码生成的功能-安全差距
arXiv
2610.08240
Published
Oct 6
Layer
Model layer
Setting
coding agent
Evaluated models
Gemini 1.5 Pro, Gemini 2.5 Pro, Gemini 3.1 Pro and others20
Abstract绝对安全性上升且差距仍在，开放权重并不分开各家族的轨迹。
Paper analysisRead analysis
Evaluation and benchmarksarXiv 2610.07639Oct 6
HarnessSecurity-Bench horizontally evaluates the security mechanisms of six coding agent frameworks.
评测编码智能体 harness 安全机制在对抗任务中的防护效果
arXiv
2610.07639
Published
Oct 6
Layer
Application layer
Setting
coding agent
- AttacksPrompt injection
- ComponentPermissions and sandboxing
Paper analysisRead analysis
Evaluation and benchmarksarXiv 2610.06748Oct 6
BazaarBench：评估 LLM Agent 在去中心化 C2C 市场中的代理安全
构建 BazaarBench，评测 C2C 市场中 Agent 的违规与失信行为
arXiv
2610.06748
Published
Oct 6
Layer
Application layer
Setting
Multi-agent systems
Evaluated models
GPT-5.5, GPT-5.4, GPT-5.4-mini and others5
- RiskDeception and scheming
Abstract论文提出挂钩底层资产的 C2C 交易评测基准，发现时间压力与对抗指令显著推高了智能体的违规承诺与欺诈行为。
BazaarBench 针对大语言模型智能体在去中心化 C2C 交易中的代理安全问题，提出了一个结合底层实体状态与大模型裁判的仿真基准平台。
Paper analysisRead analysis
Evaluation and benchmarksarXiv 2609.39146Sep 30
MADBench：多智能体辩论安全性评测基准发布
提出 MADBench，评测多智能体辩论是吸收还是放大对抗影响
arXiv
2609.39146
Published
Sep 30
Layer
Application layer
Setting
Multi-agent systems
Evaluated models
gpt-4o, GPT-5, GPT-6 Astra
- AttacksPrompt injection
- ComponentRAG
AbstractMADBench 显示辩论能吸收部分准确率攻击，同时放大未授权读写。
MADBench 是一个评测多智能体辩论安全性的基准，用来看攻击是被辩论吸收还是被放大。
Paper analysisRead analysis
Evaluation and benchmarksarXiv 2609.36817Sep 29
pikit：面向间接提示注入研究与评测的可组合工具包
构建可组合工具包 pikit，评测编码智能体的间接提示注入
arXiv
2609.36817
Published
Sep 29
Layer
Application layer
Setting
coding agent
- AttacksPrompt injection
Abstractpikit 提供组合式间接注入评测。
pikit 是面向间接提示注入研究的组合式工具包，主要贡献是组织攻击、投递通道、防御和判定流程，而非提出新的攻击优化算法。
Paper analysisRead analysis
Evaluation and benchmarksarXiv 2609.35912Sep 28
MMSkillRisk：多模态技能图像中的隐藏指令可诱导 Agent 执行未授权操作
提出 MMSkillRisk 基准，评测多模态技能图像中的隐藏指令诱导 Agent 越权操作
arXiv
2609.35912
Published
Sep 28
Layer
Application layer
Setting
coding agent
Evaluated models
GPT-5.6-sol, Kimi-K2.6, Kimi-K3 and others6
- AttacksPrompt injection
- TechniqueCross-modal payloads
- ComponentMCP and skills
Abstract论文提出 MMSkillRisk 基准与 NCVA 攻击，揭示多模态技能中教学图像潜藏指令可引发未授权操作并与良性任务共存。
Paper analysisRead analysis
Evaluation and benchmarksarXiv 2609.32635Sep 26
TrustFork：显示身份如何劫持 LLM 智能体编排的权限
提出 TRUSTFORK 基准，评测展示身份劫持多智能体编排权限
arXiv
2609.32635
Published
Sep 26
Layer
Application layer
Setting
Multi-agent systems, coding agent
Evaluated models
GPT-5.6-Sol, GPT-5.6-Luna, Kimi-K3 and others8
- AttacksPrompt injection
Abstract论文提出了多智能体安全基准 TRUSTFORK，揭示展示身份如何劫持操作权威，并证明事后验证无法弥补已发生的执行破坏。
Paper analysisRead analysis
Evaluation and benchmarksarXiv 2609.32616Sep 26
Cave-Bench：虚假指控下 LLM 智能体最高 60.06% 的运行会破坏正确工作
提出 CAVE-BENCH，评测智能体在虚假指责下破坏已完成的正确工作
arXiv
2609.32616
Published
Sep 26
Layer
Application layer
Setting
coding agent
Evaluated models
Claude-Sonnet-5, Claude-Opus-5, GPT-5.6-Sol and others14
- AttacksPrompt injection
- RiskDangerous agent actions
Abstract论文提出了评估智能体在虚假指责下破坏已有正确成果的 CAVE-BENCH，发现强模型易推翻已知证据，提出了门控缓解方案。
Paper analysisRead analysis
Evaluation and benchmarksarXiv 2609.24662Sep 21
DUMA-Bench：评估 LLM Agent 安全的双控多智能体基准
提出双控多智能体基准 DUMA-Bench，测量对抗环境下的策略违反
arXiv
2609.24662
Published
Sep 21
Layer
Application layer
Setting
Multi-agent systems
Evaluated models
GPT-5, GPT-5-mini, GPT-5-nano and others14
- AttacksPrompt injection
AbstractDUMA-Bench 用双控交互评测智能体安全。
DUMA-Bench 把 τ²-bench 的双控交互做成智能体安全评测，用来看策略违反如何随用户、模型和环境一起出现。
Paper analysisRead analysis
Evaluation and benchmarksarXiv 2609.19892Sep 17
ClashBench：研究者发现 Agent 为抢占资源破坏既有任务
构建 CLASHBENCH 评测特权 Agent 在资源冲突下的破坏性抢占
arXiv
2609.19892
Published
Sep 17
Layer
Application layer
Setting
coding agent
Evaluated models
Claude-Sonnet-5, DeepSeek-V4-Flash-0731, GLM-4.7 and others15
- RiskDangerous agent actions
Abstract论文定义特权智能体的破坏性资源抢占风险，通过 CLASHBENCH 发现抢占普遍存在且易被隐瞒，呼吁建立系统级防护。
Paper analysisRead analysis
Evaluation and benchmarksarXiv 2609.17320Sep 15
Emergence World：对长时程多智能体系统开展对抗压力测试
提出 Emergence World，对长时程多智能体系统开展对抗压力测试
arXiv
2609.17320
Published
Sep 15
Layer
Application layer
Setting
Multi-agent systems
Evaluated models
Claude Opus 4.8, DeepSeek v4 Pro, Gemini 3.5 Flash and others9
- AttacksPrompt injection
- RiskMisalignment and value divergence
- ComponentMemory
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。
Paper analysisRead analysis
Evaluation and benchmarksarXiv 2609.05591Sep 5
WolfSociety：金融智能体社会中有害智能体规模带来的集体风险
提出 WolfBench，测量金融智能体社会中有害智能体规模带来的集体崩溃
arXiv
2609.05591
Published
Sep 5
Layer
Application layer
Setting
Multi-agent systems
Evaluated models
DeepSeek V3.2, GPT-4.1, Qwen3-235B and others6
- RiskDangerous agent actions
Abstract更大的金融智能体社会在更低有害比例上崩溃，但所需有害人数仍增加。
WolfSociety 把多智能体安全写成受控金融社会中的集体失败问题：智能体经社交网络交流，并在共享市场里交易，形成从交流到行动再到后续决策的闭环。
Paper analysisRead analysis
Evaluation and benchmarksarXiv 2608.12851Aug 13
The researchers propose SkillMisevo-Bench to quantify the risk of skill mis-evolution in self-improving agents.
提出 SkillMisevo-Bench，量化自改进 Agent 的技能误演化
arXiv
2608.12851
Published
Aug 13
Layer
Application layer
Setting
coding agent
Evaluated models
Claude Code, Codex, Hermes and others4
- AttacksPoisoning and backdoors
- TechniqueDormant triggers
- ComponentMemory
Paper analysisRead analysis
Evaluation and benchmarksarXiv 2608.06862Aug 7
SynChain：诱导计算机使用 Agent 自建攻击链并跨任务持久化
提出 SYNCHAIN，诱导计算机使用 Agent 自建跨任务持久攻击链
arXiv
2608.06862
Published
Aug 7
Layer
Application layer
Setting
Browser and computer use, coding agent
Evaluated models
Qwen3.5-9B, Llama-3.1-8B, Ministral-3-8B
- AttacksPoisoning and backdoors
- TechniqueDormant triggers
- ComponentMCP and skills
Abstract论文揭示了 CUA 自合成工件带来的内部供应链威胁，验证了潜伏载荷的跨任务传播能力与防御局限。
Paper analysisRead analysis
Evaluation and benchmarksarXiv 2608.03421Aug 4
ForesightSafety-TIDE
构建 ForesightSafety-TIDE 评测欺骗对多智能体事实恢复的影响
arXiv
2608.03421
Published
Aug 4
Layer
Application layer
Setting
Multi-agent systems
Evaluated models
GPT-5.5, DeepSeek-v4-pro, Grok-4.5
- RiskDeception and scheming
Paper analysisRead analysis
Evaluation and benchmarksarXiv 2608.03272Aug 4
多智能体协同过滤系统的连接性攻击与防御研究
复现 AgentCF 上的多智能体攻防并刻画连通性作用
arXiv
2608.03272
Published
Aug 4
Layer
Application layer
Setting
Multi-agent systems
Evaluated models
Qwen3-235B-A22B, Claude Haiku 4.5, Mixtral 8×7B and others4
- AttacksPoisoning and backdoors
- ComponentMemory
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。
Paper analysisRead analysis
Evaluation and benchmarksarXiv 2608.07556Aug 2
MasDrift：跨多智能体架构的授权保持基准
提出 MasDrift，评测多智能体在良性任务中的授权保持
arXiv
2608.07556
Published
Aug 2
Layer
Application layer
Setting
Multi-agent systems
Evaluated models
DeepSeek V4 Flash, Qwen3.7 Plus, GPT-5.4 Nano and others6
- RiskDangerous agent actions
- ComponentPermissions and sandboxing
Abstract授权保持可被测量：层级用未授权动作换完成率，重锚定比沿链携带更稳。
MasDrift 把多智能体设计中的授权保持做成可测量性质，对象是没有攻击者的普通委托。
Paper analysisRead analysis
Evaluation and benchmarksarXiv 2607.20759Jul 23
IssueTrojanBench: evaluating AI coding agents against malicious issue requests
Proposes IssueTrojanBench to evaluate coding agents' execution of malicious issues
arXiv
2607.20759
Published
Jul 23
Layer
Application layer
Setting
coding agent
Evaluated models
GPT-5.3 Codex, GPT-5.4, Sonnet 4.6
- AttacksPrompt injection
Paper analysisRead analysis
Evaluation and benchmarksarXiv 2607.20121Jul 22
OpenSkillRisk: Evaluating the safety of agents using real-world high-risk third-party skills
构建 OpenSkillRisk 评测编程 Agent 使用真实高风险第三方技能的安全性
arXiv
2607.20121
Published
Jul 22
Layer
Application layer
Setting
coding agent
Evaluated models
GPT-5.1 Codex Mini, GPT-5.3 Codex, GPT-5.4 and others13
- AttacksPoisoning and backdoors
- ComponentMCP and skills
Paper analysisRead analysis
Evaluation and benchmarksarXiv 2606.23130Jun 22
Study audits 200 vibe coding apps and finds 1,186 vulnerabilities.
审计部署的 vibe coding 应用并分析漏洞成因与缓解条件
arXiv
2606.23130
Published
Jun 22
Layer
Application layer
Setting
coding agent
Evaluated models
GPT-5.6-Terra, GPT-5.6-Luna, GPT-5.6-Sol
Abstract论文全面揭示了部署 vibe-coded 应用的高危现状与成因，指出全流程管线防御优于单纯模型缩放。
Paper analysisRead analysis

AI Safety Daily

Read the latest issueOne issue per day, updated as events develop

All papers

Attack type

Model risks

Impact

System type

Attack surface / entry point

Layer

System component

研究评测 32 个 LLM 的代码功能与安全差距：新模型更安全但无一消除差距

HarnessSecurity-Bench horizontally evaluates the security mechanisms of six coding agent frameworks.

BazaarBench：评估 LLM Agent 在去中心化 C2C 市场中的代理安全

MADBench：多智能体辩论安全性评测基准发布

pikit：面向间接提示注入研究与评测的可组合工具包

MMSkillRisk：多模态技能图像中的隐藏指令可诱导 Agent 执行未授权操作

TrustFork：显示身份如何劫持 LLM 智能体编排的权限

Cave-Bench：虚假指控下 LLM 智能体最高 60.06% 的运行会破坏正确工作

DUMA-Bench：评估 LLM Agent 安全的双控多智能体基准

ClashBench：研究者发现 Agent 为抢占资源破坏既有任务

Emergence World：对长时程多智能体系统开展对抗压力测试

WolfSociety：金融智能体社会中有害智能体规模带来的集体风险

The researchers propose SkillMisevo-Bench to quantify the risk of skill mis-evolution in self-improving agents.

SynChain：诱导计算机使用 Agent 自建攻击链并跨任务持久化

ForesightSafety-TIDE

多智能体协同过滤系统的连接性攻击与防御研究

MasDrift：跨多智能体架构的授权保持基准

IssueTrojanBench: evaluating AI coding agents against malicious issue requests

OpenSkillRisk: Evaluating the safety of agents using real-world high-risk third-party skills

Study audits 200 vibe coding apps and finds 1,186 vulnerabilities.