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

Oct 12 · Monday

All papers

Found 15 papers

Filter5

Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 248papers have no tags yet and are not included in filtered results.

Attack technique：Dormant triggers System type：coding agent System type：science agent System type：Multi-agent systems System type：Embodied systems and robotics Clear all

Another 248papers do not have category tags yet and are not included in filtered results.

AttacksarXiv 2610.07510Oct 6
PersistBD: attackers can strengthen backdoors before release so that they maintain high attack success rates even after developer SFT and RL.
提出 PERSISTBD，发布前强化供应链后门使其经良性 SFT 与 RL 后仍外发凭据
arXiv
2610.07510
Published
Oct 6
Layer
Application layer
Setting
coding agent
Evaluated models
Qwen2.5-Coder-3B-Instruct, Qwen2.5-Coder-7B-Instruct, Qwen3-Coder-30B-A3B-Instruct
- AttacksPoisoning and backdoors
- TechniqueDormant triggers
- ComponentFine-tuning and open weights
Abstract总结了论文关于后门在 SFT/RL 中存活的发现、两因子机制、PERSISTBD 方法与核心数字。
本文研究第三方 LLM 智能体在开发者进行良性监督微调（SFT）和强化学习（RL）后训练时的后门持久性风险。
Paper analysisRead analysis
AttacksarXiv 2610.05793Oct 5
研究者训练出按多智能体拓扑触发的代码后门模型
提出拓扑条件后门，使代码模型在推断多智能体部署时植入漏洞
arXiv
2610.05793
Published
Oct 5
Layer
Training and data layer
Setting
coding agent
Evaluated models
Qwen2.5-7B-Instruct, Qwen2.5-Coder-7B-Instruct
- AttacksPoisoning and backdoors
- TechniqueDormant triggers
- ComponentFine-tuning and open weights
Abstract论文证实了拓扑条件后门的可训练性与泛化性，展示了常规评测盲区，并提出差异化拓扑审计作为检测防御方向。
Paper analysisRead analysis
AttacksarXiv 2609.38270Sep 29
VirusCascade：劫持 LLM 推荐智能体的协同反思机制
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
arXiv
2609.38270
Published
Sep 29
Layer
Application layer
Setting
Multi-agent systems
Evaluated models
AgentCF, AgentSEQ, AgentRAG and others4
- AttacksPoisoning and backdoors
- TechniqueDormant triggers
- ComponentMemory
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。
Paper analysisRead analysis
AttacksarXiv 2609.22711Sep 19
UBA-ORL：针对离线强化学习的遗忘激活后门攻击
提出 UBA-ORL，以 BD/CM 样本在遗忘后激活离线 RL 后门
arXiv
2609.22711
Published
Sep 19
Layer
Training and data layer
Setting
Embodied systems and robotics
Evaluated models
TD3+BC, BCQ, IQL
- AttacksPoisoning and backdoors
- TechniqueDormant triggers
AbstractUBA-ORL 用竞争的 BD/CM 样本，使离线 RL 后门在删除伪装轨迹后激活。
UBA-ORL 研究离线强化学习中由合规轨迹删除激活的后门：合法贡献者同时上传共享触发的后门轨迹和伪装轨迹，训练后触发响应被压低，删除伪装批次后再升高。受害系统是使用静态数据集和轨迹级遗忘接口的离线 RL 服务。对手不能看到训练算法、参数、梯度或具体遗忘算法，但能提交可区分批次，并在部署时向观测注入预定触发。
Paper analysisRead analysis
AttacksarXiv 2609.13889Sep 12
PMPA：针对 OpenClaw 与 Claude Code 的持久记忆投毒攻击
提出 PMPA，经外部源向 Agent 持久记忆投毒并跨会话泄露隐私
arXiv
2609.13889
Published
Sep 12
Layer
Application layer
Setting
coding agent
Evaluated models
DeepSeek-V4-Flash, DeepSeek-V4-Pro, Qwen3-Max
- AttacksPoisoning and backdoors
- TechniqueDormant triggers
- ComponentMemory
Abstract论文提出了持久记忆投毒攻击 PMPA，报告了 harness 智能体在处理外部数据时易受跨会话记忆投毒与隐私泄露的风险。
Paper analysisRead analysis
AttacksarXiv 2609.07051Sep 7
TrojanWorld：通过想象引导对世界模型智能体植入后门
提出 TrojanWorld，用物理触发器对世界模型智能体植入想象引导后门
arXiv
2609.07051
Published
Sep 7
Layer
Training and data layer
Setting
Embodied systems and robotics
Evaluated models
TD-MPC2, DreamerV3, R2-Dreamer
- AttacksPoisoning and backdoors
- TechniqueDormant triggers
- ComponentFine-tuning and open weights
AbstractTrojanWorld 揭示了世界模型智能体的供应链后门风险，通过在世界模型中操纵想象可实现对闭环动作的持续控制。
Paper analysisRead analysis
AttacksarXiv 2609.01222Sep 1
Researchers propose context privilege escalation attack, affecting 12 agent frameworks
提出针对 Agent Harness 的上下文特权提升攻击
arXiv
2609.01222
Published
Sep 1
Layer
Application layer
Setting
coding agent
Evaluated models
GPT-5.5, GPT-5.4 mini, Claude-Sonnet-4.6 and others7
- AttacksPrompt injection
- TechniqueDormant triggers
- ComponentMemory
Paper analysisRead analysis
AttacksarXiv 2608.25776Aug 26
EvoMal attack uses self-poisoning of self-evolving coding agents to achieve worm-like propagation
提出 EVOMAL，诱导自演化编码 Agent 在创建技能时自我投毒并蠕虫传播
arXiv
2608.25776
Published
Aug 26
Layer
Application layer
Setting
coding agent
Evaluated models
Devstral-Small-2, Gemma-4-31B-IT, Qwen3-Coder-Next and others7
- AttacksPoisoning and backdoors
- TechniqueDormant triggers
- ComponentMCP and skills
Abstract论文指出了自演化智能体模仿检索代码的自我毒化漏洞，提出 EVOMAL 攻击与防御，阐明了供应链新风险。
Paper analysisRead analysis
Evaluation and benchmarksarXiv 2608.12851Aug 13
研究者提出 SkillMisevo-Bench，量化自改进 Agent 的技能误演化风险
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
AttacksarXiv 2608.09577Aug 10
ElasticBack：通过触发词与规则耦合在 LLM Agent 技能中植入条件后门
提出 ElasticBack，在单个 Agent 技能中植入条件后门
arXiv
2608.09577
Published
Aug 10
Layer
Application layer
Setting
coding agent
Evaluated models
GLM-5.2, MiniMax-M3, GPT-5.4 and others4
- AttacksPoisoning and backdoors
- TechniqueDormant triggers
- ComponentMCP and skills
AbstractElasticBack 用冻结规则加遗传搜索演化 trigger，在单 skill 上做条件后门。
ElasticBack 是放在 LLM agent 单个 skill 里的条件后门攻击。。
Paper analysisRead analysis
AttacksarXiv 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
AttacksarXiv 2606.09499Jun 8
研究者提出针对世界模型的机器人学习管线投毒攻击
提出 VPH 与 VTH，只改视频帧劫持世界模型并投毒下游策略
arXiv
2606.09499
Published
Jun 8
Layer
Training and data layer
Setting
Embodied systems and robotics
Evaluated models
Cosmos-Predict 2.5, Cosmos-Predict 2.5 AC, Dino WM and others4
- AttacksPoisoning and backdoors
- TechniqueGradient and representation optimization
- ComponentVideo
Abstract只改视频帧经世界模型投毒。
只改看似安全的视频帧，经世界模型之后才改变下游机器人策略。 问题在于世界模型进入数据生成后，数据集检查看到的仍是安全演示，合成轨迹却可以变危险。
Paper analysisRead analysis
AttacksarXiv 2605.08460May 9
论文建模多智能体网络中的子智能体继承攻击面
建模并利用多智能体网络中子智能体生成时的记忆继承漏洞
arXiv
2605.08460
Published
May 9
Layer
Application layer
Setting
Multi-agent systems
Evaluated models
MiniMax M2.5, Llama-4-Maverick-17B-128E-Instruct-FP8, Qwen3.5-Plus and others5
- AttacksPoisoning and backdoors
- TechniqueDormant triggers
- ComponentMemory
Abstract形式化子智能体继承，在 OpenClaw 上演示四类编排层漏洞并提出防御。
作者对多智能体网络里的子智能体继承做形式化分析，并用开源框架上的 PoC 演示编排层如何让单点妥协继续扩散。
Paper analysisRead analysis
AttacksarXiv 2604.03890Apr 5
From prompts to physical actions: structured backdoor attacks against LLM-mediated robot control systems
Propose a structured JSON backdoor that triggers malicious actions in robot control via a poisoned LoRA
arXiv
2604.03890
Published
Apr 5
Layer
Training and data layer
Setting
Embodied systems and robotics, LLM applications
Evaluated models
Llama-3.1-8B-Instruct, Gemma-2-9B-IT, DeepSeek-R1-Distill-Llama-8B and others4
- AttacksPoisoning and backdoors
- TechniqueDormant triggers
- ComponentFine-tuning and open weights
Abstract推理层后门传不到执行。
Paper analysisRead analysis
AttacksarXiv 2601.00240Jan 1
When agents view humans as out-group: belief-dependent bias in LLM-driven agents
提出 BPA 改写 profile 与记忆，重新诱发智能体对人类的外群体偏向
arXiv
2601.00240
Published
Jan 1
Layer
Application layer
Setting
Multi-agent systems
Evaluated models
gpt-4o-mini
- AttacksPoisoning and backdoors
- RiskBias and discrimination
- TechniqueDormant triggers
- ComponentMemory
Abstract最小群体线索下出现内群体偏向。
作者考察 LLM 智能体在任意群体边界下会不会把人类当外群体，并用信念投毒检验面向人类的抑制是否依赖身份信念。
Paper analysisRead analysis

You have reached the end

AI Safety Daily

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

All papers

Attack type

Attack technique

Impact

System type

Attack surface / entry point

Layer

System component

PersistBD: attackers can strengthen backdoors before release so that they maintain high attack success rates even after developer SFT and RL.

研究者训练出按多智能体拓扑触发的代码后门模型

VirusCascade：劫持 LLM 推荐智能体的协同反思机制

UBA-ORL：针对离线强化学习的遗忘激活后门攻击

PMPA：针对 OpenClaw 与 Claude Code 的持久记忆投毒攻击

TrojanWorld：通过想象引导对世界模型智能体植入后门

Researchers propose context privilege escalation attack, affecting 12 agent frameworks

EvoMal attack uses self-poisoning of self-evolving coding agents to achieve worm-like propagation

研究者提出 SkillMisevo-Bench，量化自改进 Agent 的技能误演化风险

ElasticBack：通过触发词与规则耦合在 LLM Agent 技能中植入条件后门

SynChain：诱导计算机使用 Agent 自建攻击链并跨任务持久化

研究者提出针对世界模型的机器人学习管线投毒攻击

论文建模多智能体网络中的子智能体继承攻击面

From prompts to physical actions: structured backdoor attacks against LLM-mediated robot control systems

When agents view humans as out-group: belief-dependent bias in LLM-driven agents