Skip to content

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

Oct 12 · Monday

All papers

Found 3 papers
Filter3

Defense type

Inference-time intervention3Detection and filtering16Instruction–data separation8Permissions and approval15Monitoring and auditing11

Attack surface / entry point

User input3

Layer

Model layer19Application layer3
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 262papers have no tags yet and are not included in filtered results.
Defense type：Inference-time interventionAttack surface / entry point：User inputLayer：Application layerClear all

Another 262papers do not have category tags yet and are not included in filtered results.

  1. DefensesarXiv 2606.22673

    Agent MechSuits：面向多轮 CLI Agent 的机制子空间安全引导

    提出 Agent MechSuits，对多轮 CLI Agent 做步级检测与子空间转向

    arXiv
    2606.22673
    Published
    Layer
    Application layer
    Setting
    coding agent
    Evaluated models
    LLaMA-3.1-8B, Qwen-2.5-7B, Gemma-2-9B
    Abstract白盒步级探针加稀疏转向可压低三模型恶意动作，同时提高生成崩溃率。

    Agent MechSuits 是面向多轮 CLI 智能体的白盒、步级表示防御，并配有可执行轨迹基准 MAS。

    Paper analysisRead analysis
  2. DefensesarXiv 2606.18673

    Understanding and mitigating prompt leakage attacks in real-world LLM applications

    Propose soft prompt defense AREA, re-anchoring attention to mitigate system prompt leakage

    arXiv
    2606.18673
    Published
    Layer
    Application layer
    Setting
    LLM applications
    Attacker
    Black-box
    Evaluated models
    Llama-2-7B-chat-hf, Llama-3.1-8B-Instruct, Mistral-7B-Instruct-v0.3 and others8
    AbstractThe authors measure commercial prompt leakage, propose attention drift, and use AREA to strike a trade-off between usability and leakage resistance.

    The authors study system prompt leakage in real LLM applications and propose AREA, a mitigation method that does not modify weights.

    Paper analysisRead analysis
  3. DefensesarXiv 2606.08234

    SciTrace：面向科学发现智能体的轨迹感知安全推理框架

    提出 SciTrace，为科学发现智能体加入跨阶段安全推理与工具轨迹核验

    arXiv
    2606.08234
    Published
    Layer
    Application layer
    Setting
    science agent, Multi-agent systems
    Evaluated models
    Llama-3.1-70B-Instruct, Qwen2.5-72B-Instruct, DeepSeek-V3 and others4
    AbstractSciTrace 把安全推理织入科学智能体各阶段，在 SciSafetyBench 上提高安全指标并保持输出质量。

    SciTrace 是加在科学发现智能体流水线上的安全框架，不是再在各阶段出口放一个独立过滤器。

    Paper analysisRead analysis
You have reached the end