Skip to content

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

Oct 12 · Monday

All papers

Found 7 papers
Filter5
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 254papers have no tags yet and are not included in filtered results.

Another 254papers do not have category tags yet and are not included in filtered results.

  1. AttacksarXiv 2610.04985

    研究揭示 Jev 作为应用决策层的安全与隐私风险

    评估应用决策层的输入注入与隐私推断风险

    Published
    Evaluated models
    Jev, NanoJev
    AbstractJev 的类型化决策可被输入与训练操纵,也会泄露信息,并同时支持检测与滥用。

    Jev 是 TypeSafe 的 System One 模型,把应用 state 和固定问题变成 Choice、Noul 或 Score 的类型化决策与概率。作者用官方 API 和可改训练的 NanoJev,考察它作为决策层时的操纵、泄露与双重用途。

    Paper analysisRead analysis
  2. AttacksarXiv 2608.25776

    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

    Published
    Evaluated models
    Devstral-Small-2, Gemma-4-31B-IT, Qwen3-Coder-Next and others7

    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
  3. AttacksarXiv 2607.14493

    LogInject 框架披露 LLM 日志分析中的被动提示注入

    提出 LogInject 框架,评测日志分析中的被动提示注入及缓解

    Published
    Evaluated models
    GPT-4o, Claude 3.5 Sonnet, Llama-3-70B-Instruct

    Abstract论文评估了 LLM 日志分析中的上下文污染风险,提出分片拼接等攻击与三层防御,指出必须结合架构隔离与人工介入。

    Paper analysisRead analysis
  4. AttacksarXiv 2607.12340

    Research: LLM agent skill-name hallucination rates reach up to 62%, which can be exploited via squatting for supply-chain attacks

    提出技能名称抢注攻击,利用 Agent 虚构技能名实施供应链劫持

    Published
    Evaluated models
    GLM-4.5-Air, GPT-5.4-mini, Claude Sonnet 4.6 and others12
    Abstract研究证实智能体虚构技能名具有高发生率与可预测性,现有防御难以兼顾安全与效用,亟需注册表结构性防护。

    本研究系统揭示了大模型智能体技能推荐场景下的虚构技能名称安全风险,将其形式化为一种新型供应链抢注攻击。

    Paper analysisRead analysis
  5. AttacksarXiv 2605.24421

    研究者提出日志型提示注入攻击,可抑制 SOC 中 LLM 分析助手的恶意日志识别

    提出日志基底提示注入,操纵 SOC 分析员的分类、摘要与处置建议

    Published
    Evaluated models
    gpt-4o-mini

    Abstract在 gpt-4o-mini 上,人格劫持与上下文操纵可改写 SOC 分析输出,直接覆盖在分类上无效。

    Paper analysisRead analysis
You have reached the end