Skip to content

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

Oct 12 · Monday

All papers

Found 9 papers
Filter4

Attack type

Poisoning and backdoors4

System type

Models and APIs4AI Agent29coding agent5Multi-agent systems4

Attack surface / entry point

User input3

Layer

Application layer5

System component

MCP and skills6Memory5Guardrails and judges32Monitors14Reasoning chains8Permissions and sandboxing3Fine-tuning and open weights4Vision20Audio8Video7Image generation7Multimodal36
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 233papers have no tags yet and are not included in filtered results.
System type：Models and APIsSystem type：coding agentSystem component：MemorySystem component：Fine-tuning and open weightsClear all

Another 233papers do not have category tags yet and are not included in filtered results.

  1. Evaluation and benchmarksarXiv 2610.08902

    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
    Layer
    Application layer
    Setting
    coding agent
    Evaluated models
    Claude Fable 5, Claude Opus 5, GPT-5.6 Sol and others10
    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
  2. Evaluation and benchmarksarXiv 2609.39473

    FAME：用反事实推理评测自主智能体的虚假记忆

    提出 FAME，用反事实概念漂移评测智能体虚假记忆

    arXiv
    2609.39473
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Evaluated models
    Llama-3B
    AbstractFAME 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。。

    Paper analysisRead analysis
  4. Evaluation and benchmarksarXiv 2608.08542

    SkillSafe-Bench：技能合并模型静态安全无法预测自适应越狱鲁棒性

    提出 SkillSafe-Bench，评测技能合并模型的自适应越狱鲁棒性

    arXiv
    2608.08542
    Published
    Layer
    Prompt layer
    Setting
    Models and APIs
    Evaluated models
    Qwen2.5-7B-Instruct, Llama-3.1-8B-Instruct, Mistral-7B-Instruct-v0.3 and others6
    Abstract论文报告了技能合并大模型在静态安全与自适应越狱间的脱节，提出了评测基准与无数据子空间投影修复方法。

    本研究针对开源语言模型技能合并过程中的安全评估盲区，系统评测并刻画了合并大模型在自适应越狱攻击下的脆弱性特征。

    Paper analysisRead analysis
  5. Evaluation and benchmarksarXiv 2608.06862

    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
    Layer
    Application layer
    Setting
    Browser and computer use, coding agent
    Evaluated models
    Qwen3.5-9B, Llama-3.1-8B, Ministral-3-8B

    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
  6. Evaluation and benchmarksarXiv 2608.04830

    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
    Layer
    Application layer
    Setting
    coding agent
    Evaluated models
    DeepSeek-V4-Pro, GPT-5.5, GLM-5.1 and others5
    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
  7. Evaluation and benchmarksarXiv 2607.14611

    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
    Layer
    Application layer
    Setting
    coding agent
    Evaluated models
    Claude Haiku 4.5, Claude Opus 4.7, GPT-5.2 and others4
    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
  8. Evaluation and benchmarksarXiv 2605.14605

    Study: malicious fine-tuning defenses fail under continued training, harmfulness rises across all 72 defense trajectories

    用代价曲线评估恶意微调防御在持续训练下的衰减

    arXiv
    2605.14605
    Published
    Layer
    Training and data layer
    Setting
    Models and APIs
    Evaluated models
    Llama-2-7B-chat, Qwen3-8B, Llama-3.1-8B-Instruct and others8

    Abstract论文指出恶意微调防御在持续训练下均会衰减，表明基于有限攻击者假设的防御无法为开源模型提供持久保护。

    Paper analysisRead analysis
  9. Evaluation and benchmarksarXiv 2511.18921

    BackdoorVLM：面向视觉语言模型后门攻击与防御的基准

    提出 BackdoorVLM 基准，评测视觉语言模型微调中的后门攻击与防御

    arXiv
    2511.18921
    Published
    Layer
    Training and data layer
    Setting
    Models and APIs
    Evaluated models
    LLaVA-1.5-7B, Qwen2.5-VL-7B
    AbstractBackdoorVLM 统一评测 VLM 后门与防御：含文本触发在低投毒率下更易激活，现有防御跨类型不稳定。

    BackdoorVLM 是作者提出的 VLM 后门攻击与防御评测基准，作者称它是首个此类综合基准。

    Paper analysisRead analysis
You have reached the end