Skip to content

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

Oct 12 · Monday

All papers

Found 10 papers
Filter4

Attack type

Prompt injection5

Impact

Unauthorized actions50Data and privacy leaks14Output manipulation10Availability and reliability8Oversight failure17Increased misuse capability5

System type

LLM applications58AI Agent89coding agent8science agent6web agent5Browser and computer use2Multi-agent systems25

Layer

Application layer10
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 261papers have no tags yet and are not included in filtered results.
Impact：Output manipulationSystem type：coding agentSystem type：Browser and computer useLayer：Application layerClear all

Another 261papers do not have category tags yet and are not included in filtered results.

  2. AttacksarXiv 2610.09264

    研究者提出 PackHallu：经规则文件提示注入对编码 Agent 发起包幻觉攻击

    提出 PackHallu，经规则文件提示注入诱导编码 Agent 换用攻击者指定包

    arXiv
    2610.09264
    Published
    Layer
    Application layer
    Setting
    coding agent
    Evaluated models
    Qwen2.5-Coder-7B, Qwen3-Coder-30B, Devstral-Small-2-24B and others19
    AbstractPackHallu 诱导规则文件换包。

    PackHallu 研究一种针对编程智能体规则文件的提示注入：让智能体在本应使用合法依赖时，改导入攻击者指定并控制的包。

    Paper analysisRead analysis
  3. Analysis and theoryarXiv 2610.06163

    SAGE：定位 LLM Agent 修复中最早偏离安全意图的环节

    提出 SAGE，定位代码修复 Agent 最早偏离安全意图的轮次

    arXiv
    2610.06163
    Published
    Layer
    Application layer
    Setting
    coding agent
    Evaluated models
    GPT-5.5, Claude Opus 4.8, Gemini 3.1 Pro and others6
    AbstractSAGE 在已通过检查的修复轨迹上定位静默失败的最早偏离，类型比轮次更稳定。

    SAGE 在已通过语法和功能检查、但仍含确认安全缺陷的智能体修复轨迹上，定位最早可归因的安全意图偏离。。

    Paper analysisRead analysis
  5. Evaluation and benchmarksarXiv 2610.06898

    DIBench：面向移动 GUI 智能体多候选选择决策完整性的安全基准

    用 DIBench 评测移动 GUI 智能体被 UI 注入后的决策完整性

    arXiv
    2610.06898
    Published
    Layer
    Application layer
    Setting
    Browser and computer use
    Evaluated models
    Qwen2.5-VL(32B), Qwen3-VL(32B), GUI-Owl(32B) and others7

    Abstract论文提出移动智能体决策完整性基准 DIBench，发现欺诈 UI 注入诱导目标选择并推高完成率，通用防御收益不稳定。

    Paper analysisRead analysis
  6. AttacksarXiv 2609.17817

    论文：用投毒基准污染自改进编码 Agent，令其后续版本写出漏洞代码

    提出基准投毒攻击，使自修改编码 Agent 跨代写出含漏洞代码

    arXiv
    2609.17817
    Published
    Layer
    Application layer
    Setting
    coding agent
    Evaluated models
    Claude Sonnet 4.5, Qwen3.5-397B, gpt-oss-120b and others5

    Abstract论文报告了恶意基准能污染自修改代码智能体的进化过程并持续输出漏洞，警示系统设计需纳入安全约束。

    Paper analysisRead analysis
  8. DefensesarXiv 2605.08382

    SecureForge 通过提示词优化发现并减少 LLM 生成代码漏洞

    提出 SecureForge，在推理时优化系统提示以减少编码智能体的代码弱点

    arXiv
    2605.08382
    Published
    Layer
    Application layer
    Setting
    coding agent
    Evaluated models
    Qwen 2.5 Coder 7B, Qwen 2.5 Coder 14B, Qwen3 30B-A3B and others10
    AbstractSecureForge 审计良性 CWE 失败并优化系统提示词。

    SecureForge是一条只用 API 和静态分析、在推理时加固编码模型的流水线。

    Paper analysisRead analysis
  9. Evaluation and benchmarksarXiv 2601.22952

    Filtering the Noise: A Comparative Study of LLM Agents in Vulnerability False Positive Filtering

    评测代码 Agent 过滤静态告警误报的能力

    arXiv
    2601.22952
    Published
    Layer
    Application layer
    Setting
    coding agent
    Evaluated models
    Claude Sonnet 4, DeepSeek Chat, GPT-5
    Abstract智能体可去掉大量 SAST 噪声，但收益随骨干和 CWE 变化，并会把部分真漏洞标成误报。

    这是对三种 LLM 智能体框架过滤 SAST 误报的比较研究。

    Paper analysisRead analysis
You have reached the end