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

Oct 13 · Tuesday

All papers

Found 11 papers

Filter5

Attack type

Prompt injection4 Poisoning and backdoors3

Impact

Unauthorized actions6

System type

Models and APIs36 LLM applications6 AI Agent40 coding agent5 web agent2 Multi-agent systems3 Embodied systems and robotics4

Attack surface / entry point

Images, audio and video3

Layer

Application layer9

System component

MCP and skills6 Memory4 Guardrails and judges7 Monitors11 Reasoning chains3 Permissions and sandboxing3 Vision6 Multimodal7

Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 215papers have no tags yet and are not included in filtered results.

System type：coding agent System type：web agent System type：Embodied systems and robotics System component：Memory System component：Multimodal Clear all

Another 215papers do not have category tags yet and are not included in filtered results.

Evaluation and benchmarksarXiv 2610.08902Oct 7
论文提出 agent plasticity 指标衡量智能体通过经验自我改进的效率
提出 agent plasticity 指标衡量智能体通过经验自我改进的效率
arXiv
2610.08902
Published
Oct 7
Layer
Application layer
Setting
coding agent
Evaluated models
Claude Fable 5, Claude Opus 5, GPT-5.6 Sol and others10
- ComponentMemory
Abstract作者用固定权重协议比较前沿模型把经验写成制品后的留出增益与习得效率。
作者用 agent plasticity 衡量一件事：权重冻结时，智能体把经验写成可继承制品，再换成留出能力增益，这个转换有多省。
Paper analysisRead analysis
Evaluation and benchmarksarXiv 2610.06171Oct 5
ControlPed 生成逼真行人危险动作场景，七款端到端驾驶模型 HDScore 从 88.8 降至 47.4
提出 ControlPed 与 HazardPed，生成可控行人危险场景并评测端到端驾驶
arXiv
2610.06171
Published
Oct 5
Layer
Model layer
Setting
Embodied systems and robotics
Evaluated models
DiffusionDrive, SSR, VAD and others7
- ComponentVideo
Paper analysisRead analysis
Evaluation and benchmarksarXiv 2609.38948Sep 30
DrivingBench 发布：让视觉语言模型驾驶丰田 Corolla 绕桩
提出 DrivingBench，评测通用视觉语言模型能否闭环驾驶真车
arXiv
2609.38948
Published
Sep 30
Layer
Application layer
Setting
Embodied systems and robotics
Evaluated models
GPT-6 Astra, Claude Fable 5.1, Grok 4.6 and others4
- ComponentVision
Abstract仅 Astra 第二次跑完低速锥桶路线。
DrivingBench 评测通用 VLM 能否自己闭环开真车，推理延迟也算进任务。
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 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 2608.04830Aug 5
ContextWeave：面向长周期办公工作流的智能体记忆基准
构建 ContextWeave，评测办公工作流智能体记忆的下游增益
arXiv
2608.04830
Published
Aug 5
Layer
Application layer
Setting
coding agent
Evaluated models
DeepSeek-V4-Pro, GPT-5.5, GLM-5.1 and others5
- ComponentMemory
AbstractContextWeave 用真实办公任务流检验记忆是否改善工作区质量与偏好对齐。
ContextWeave 是面向语言智能体记忆的纵向基准，用来看召回先前经验能否让后续办公任务做得更好。
Paper analysisRead analysis
Evaluation and benchmarksarXiv 2607.14611Jul 16
论文评测 Claude Code 与 Codex 记忆文件中的提示注入风险
评测编码 Agent 记忆文件中提示注入的跨会话影响
arXiv
2607.14611
Published
Jul 16
Layer
Application layer
Setting
coding agent
Evaluated models
Claude Haiku 4.5, Claude Opus 4.7, GPT-5.2 and others4
- AttacksPoisoning and backdoors
- ComponentMemory
Abstract已植入记忆文件的载荷可以跨会话影响 Claude Code 与 Codex，攻击成功与载荷是否留下是两种不同的失败。
Bad Memory 在沙箱合成工作区里评测文件型持久记忆上的提示注入，比较载荷能否改变当前会话，以及能否在后续会话中留下或叠加。
Paper analysisRead analysis
Evaluation and benchmarksarXiv 2604.12447Apr 14
HazardArena：面向 VLA 模型的语义安全评测基准
提出 HazardArena 基准，用孪生场景评测 VLA 的语义安全
arXiv
2604.12447
Published
Apr 14
Layer
Model layer
Setting
Embodied systems and robotics
Evaluated models
OpenVLA-OFT, π0, NORA and others4
- RiskDangerous agent actions
- ComponentVision
Abstractsafe-only 微调提升良性执行，也提升匹配不安全孪生上的危险完成。
HazardArena 评测 VLA 在运动要求不变时，能否因语义风险而停手。
Paper analysisRead analysis
Evaluation and benchmarksarXiv 2603.11987Mar 12
LABSHIELD：面向科学实验室安全推理与规划的多模态基准
提出 LABSHIELD，评测科学实验室智能体的安全推理与规划
arXiv
2603.11987
Published
Mar 12
Layer
Application layer
Setting
science agent, Embodied systems and robotics
Evaluated models
GPT-5.2, GPT-o3, GPT-o4-mini and others20
- RiskDangerous agent actions
- ComponentVision
Paper analysisRead analysis
Evaluation and benchmarksarXiv 2510.01354Oct 2, 2025
WAInjectBench 系统评测网页 Agent 的提示注入检测方法
提出 WAInjectBench 评测网页 Agent 的提示注入检测
arXiv
2510.01354
Published
Oct 2, 2025
Layer
Application layer
Setting
web agent
Evaluated models
GPT-4o, Mistral-7B-Instruct-v0.1, Llama-Prompt-Guard-2-86M and others8
- DefensesDetection and filtering
- AttacksPrompt injection
- ComponentGuardrails and judges
AbstractWAInjectBench 比较网页智能体的提示注入检测：显式线索可被部分检出，隐蔽攻击大多漏检。
WAInjectBench 是网页智能体提示注入检测的基准。作者要看现有检测器能否发现这类攻击：攻击者改网页，使智能体执行目标动作，而不是用户任务。作者称这是首个此类综合基准。
Paper analysisRead analysis
Evaluation and benchmarksarXiv 2406.12814Jun 19, 2024
论文提出 ARE 框架，在 VisualWebArena 上评估多模态 Agent 的对抗鲁棒性
提出 ARE 框架与图像文本攻击，评测多模态网页 Agent 的对抗鲁棒性
arXiv
2406.12814
Published
Jun 19, 2024
Layer
Application layer
Setting
web agent
Evaluated models
GPT-4o, GPT-4V, Claude-3-Opus and others4
- AttacksPrompt injection
- TechniqueGradient and representation optimization
- ComponentVision
Abstract系统评估多模态网页智能体的脆弱性，指出推理时计算组件被攻破会加剧系统风险。
Paper analysisRead analysis

You have reached the end

AI Safety Daily

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