Skip to content

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

Oct 12 · Monday

All papers

Found 8 papers
Filter3

Attack type

Prompt injection3Poisoning and backdoors3

Defense type

Model hardening11Inference-time intervention4Detection and filtering8Instruction–data separation9Permissions and approval10Monitoring and auditing5

Impact

Output manipulation4

System type

Models and APIs3AI Agent4

Attack surface / entry point

Tool responses3

Layer

Application layer5

System component

MCP and skills10Memory5RAG6Guardrails and judges68Monitors4Reasoning chains3Vision11Video3Image generation4Multimodal17
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 265papers have no tags yet and are not included in filtered results.
Defense type：Detection and filteringSystem component：MemorySystem component：Reasoning chainsClear all

Another 265papers do not have category tags yet and are not included in filtered results.

  1. DefensesarXiv 2610.07657

    DEFER1 多智能体防御研究报告受控测试中的攻击成功率下降

    实现 DEFER，以确定性检查优先拦截多智能体流水线的内容攻击

    arXiv
    2610.07657
    Published
    Layer
    Application layer
    Setting
    Multi-agent systems
    Evaluated models
    Qwen3-235B-A22B-Instruct-2507, gpt-oss-120b, Llama-4-Scout-17B-16E-Instruct and others5
    AbstractDEFER 把确定性检查放在 judge 之前。

    DEFER 用来测量多智能体授权流水线里，确定性规则在何处结束、LLM judge 从何处开始。

    Paper analysisRead analysis
  2. DefensesarXiv 2610.07403

    针对 LLM 谄媚的纵深防御：记忆门控对激活诱导与记忆诱导谄媚的评估

    评测记忆门控对激活诱导与记忆诱导谄媚的防御效果

    arXiv
    2610.07403
    Published
    Layer
    Application layer
    Setting
    LLM applications
    Evaluated models
    Llama-3.1-8B-Instruct, Qwen2.5-7B-Instruct, Mistral-7B-Instruct-v0.3 and others4
    Abstract作者称外部记忆过滤成立，数据未显示反向转向再有贡献。

    作者在四个开源指令模型上，把激活转向和外部记忆处理放进同一纵深防御协议，看记忆诱发谄媚和内部谄媚压力能否分开压低，以及个性化效用还剩多少。要处理的问题是：检索到的用户历史会推动模型顺从存储信念。只改外部上下文，并不直接动模型内部的谄媚表征。

    Paper analysisRead analysis
  3. DefensesarXiv 2609.36641

    从仅结果奖励的强化学习中诱导过程监督

    提出 TIPS，用仅结果奖励诱导生成式过程监督

    arXiv
    2609.36641
    Published
    Layer
    Training and data layer
    Setting
    Models and APIs
    Evaluated models
    Qwen3-4B-Thinking-2507, Qwen3-4B-Instruct-2507, Qwen3-8B-Thinking and others8
    Abstract结果监督的 GRPO 可诱导步骤验证。

    TIPS 用只含结果对错的强化学习训练生成式奖励模型，让步骤级验证出现在思维链里。

    Paper analysisRead analysis
  4. DefensesarXiv 2609.36562

    ThinkingGuard：通过逐步风险归因解码多模态大语言模型中的隐式危害

    构建 TriggerBench 并训练 ThinkingGuard，检测图文隐式风险

    arXiv
    2609.36562
    Published
    Layer
    Prompt layer
    Setting
    Models and APIs
    Evaluated models
    ThinkingGuard（Qwen3-VL-8B-Instruct）
    AbstractTriggerBench 隔离触发条件，ThinkingGuard 用分步归因在隐式风险检测上取得作者报告的较高平均分。

    这篇工作研究多模态隐式风险检测：图文各自良性，风险只在关键元素与触发元素交互时出现。

    Paper analysisRead analysis
  5. Evaluation and benchmarksarXiv 2609.08258

    研究实测五套 Agent 记忆系统均不执行撤销标记

    评测 Agent 记忆系统的软撤回执行情况，并提出陈旧检索防护

    arXiv
    2609.08258
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Evaluated models
    GPT-5.5, Grok-4, DeepSeek-V4-Flash and others9

    Abstract系统揭示了记忆系统软撤回在检索时普遍未执行的安全漏洞，证明写回会击穿现有防御，并提出读取端防护作为必要控制手段。

    Paper analysisRead analysis
  7. DefensesarXiv 2608.12876

    SPARED：用对抗编辑数据训练基于推理的 AI 生成图像检测器

    提出 SPARED，用对抗编辑数据训练基于推理的 AI 生成图像检测器

    arXiv
    2608.12876
    Published
    Layer
    Training and data layer
    Setting
    Models and APIs
    Attacker
    Black-box, White-box
    Evaluated models
    Qwen3.5-9B
    AbstractSPARED 用防捷径的编辑对抗环训练 9B 推理检测器。

    SPARED 是一套用于可解释 AI 生成图像检测的攻防强化学习流程，报告模型是 Qwen3.5-9B 上的第三轮防御器。

    Paper analysisRead analysis
You have reached the end