Skip to content

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

Oct 12 · Monday

All papers

Found 3 papers
Filter3

Attack surface / entry point

User input26Web pages and interfaces3Documents and messages3Tool responses3Code repositories and dependencies3Memory writes1Images, audio and video6Training data4Weights and gradients2

System component

MCP and skills7Memory35RAG3Guardrails and judges5Monitors3Reasoning chains3Permissions and sandboxing7Fine-tuning and open weights34Image generation6Multimodal9
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.
Attack surface / entry point：Memory writesAttack surface / entry point：Weights and gradientsSystem component：Reasoning chainsClear all

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

  1. DefensesarXiv 2609.38909

    Purdue 提出 Pact：将欺骗作为行为遗忘

    提出 PACT，遗忘推理模型在压力下的欺骗行为并保留上下文理解

    arXiv
    2609.38909
    Published
    Layer
    Training and data layer
    Setting
    Models and APIs
    Attacker
    White-box
    Evaluated models
    DeepSeek-R1-Distill-Qwen-32B, QwQ-32B

    Abstract论文将大模型欺骗形式化为上下文条件行为，提出 PACT 框架在消除欺骗的同时保留了上下文遵循能力。

    Paper analysisRead analysis
  3. OtherarXiv 2609.12413

    SoK 综述：智能体 AI 时代的越狱攻击、防御与实践考量

    系统梳理智能体执行链路中的越狱攻击与防御并比较推理时防御

    arXiv
    2609.12413
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Evaluated models
    Qwen3.5-4B, Llama-3.1-8B-Instruct
    AbstractSoK 将越狱重放到智能体流水线，并用两种模型检验回复层防御的边际与代价。

    Mia 等人把越狱安全从单轮回复扩展到智能体的规划、记忆、工具和智能体间通信，并问既有结论在更强原生对齐下是否还成立。

    Paper analysisRead analysis
You have reached the end