Skip to content

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

Oct 12 · Monday

All papers

Found 7 papers
Filter3

Attack type

Jailbreaks5

Attack technique

Automated search7Encoding and obfuscation7Conversation structure manipulation0Cross-modal payloads4Defense-targeted3

Impact

Harmful content5

System type

Models and APIs7

Attacker access

Black-box4

Attack surface / entry point

User input6

Layer

Prompt layer6

System component

MCP and skills18Memory5RAG7Guardrails and judges21Reasoning chains8Fine-tuning and open weights3Vision9Image generation7Multimodal19
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.
Attack technique：Automated searchAttack technique：Conversation structure manipulationSystem component：Image generationClear all

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

  3. AttacksarXiv 2609.01168

    CRACK：用多智能体辩论越狱多层安全过滤的 T2I 模型

    提出 CRACK，用多智能体辩论在黑盒下越狱文生图多层安全过滤

    arXiv
    2609.01168
    Published
    Layer
    Prompt layer
    Setting
    Models and APIs
    Attacker
    Black-box
    Evaluated models
    Stable Diffusion v1.4, SDXL, DALL·E 3 and others4
    AbstractCRACK 以分层诊断的多智能体辩论搜索多层 T2I 过滤器的联合规避区域。

    CRACK 是面向文本生成图像模型多层安全栈的黑盒越狱框架，用几何上的 Detection Surface 解释为何粗粒度反馈不够。

    Paper analysisRead analysis
  6. AttacksarXiv 2508.06837

    Prometheus：针对文生图扩散模型的免训练提示词窃取攻击

    提出 Prometheus，从展示图反推文生图模型的在售提示词

    arXiv
    2508.06837
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Attacker
    No-box (offline transfer)
    Evaluated models
    Midjourney, Leonardo.ai, DALL·E and others4
    Abstract训练无关的 proxy 搜索攻击。

    Prometheus 是针对文生图市场 showcase 的训练无关提示词窃取：攻击者看不到在售文本，只用本地开源 proxy 恢复 subject 和 modifier，并希望换 subject 后风格仍在。

    Paper analysisRead analysis
  7. AttacksarXiv 2503.01839

    研究者用微调大语言模型越狱带安全护栏的文生图模型

    提出 PromptTune，微调 LLM 改写提示以越狱文生图护栏

    arXiv
    2503.01839
    Published
    Layer
    Prompt layer
    Setting
    Models and APIs
    Attacker
    No-box (offline transfer)
    Evaluated models
    SDXL-Turbo, MACE, SafeGen
    AbstractLLM 改写可提高过滤器绕过率。

    PromptTune 用微调 LLM 改写提示词，攻击带安全过滤器或对齐的文生图模型。

    Paper analysisRead analysis
You have reached the end