Skip to content

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

Oct 12 · Monday

All papers

Found 6 papers
Filter4

Attack type

Detection evasion3

Attack technique

Gradient and representation optimization35Automated search29Multi-turn escalation5Encoding and obfuscation22Role-play and persuasion6Reasoning-chain manipulation3Cross-modal payloads59Defense-targeted6Dormant triggers16

Impact

Output manipulation4

System type

Models and APIs5

Attacker access

Black-box3

Attack surface / entry point

User input21Web pages and interfaces1Documents and messages1Tool responses4Tool and skill descriptions7Images, audio and video5Training data7Weights and gradients7Distribution channels7

Layer

Model layer3

System component

Image generation3Multimodal4
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 240papers have no tags yet and are not included in filtered results.
Attack technique：Defense-targetedAttack surface / entry point：Web pages and interfacesAttack surface / entry point：Documents and messagesAttack surface / entry point：Images, audio and videoClear all

Another 240papers do not have category tags yet and are not included in filtered results.

  1. AttacksarXiv 2610.03166

    LiBRA：通过双向隐空间优化实现检测感知的图像水印去除

    提出 LiBRA，在潜空间双向优化以规避图像水印双侧检测

    arXiv
    2610.03166
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Attacker
    White-box
    Evaluated models
    Stable Signature, YU1, HiDDeN and others4

    AbstractLiBRA 用双向潜空间优化规避双侧水印检测，并提高相对反转基线的保真。

    Paper analysisRead analysis
  2. AttacksarXiv 2609.22510

    特拉维夫大学提出爆炸性提示词：条件触发的间接提示注入可绕过九款生产 Agent

    提出条件触发的爆炸提示词，并设计摄入期检测器 DeFuse

    arXiv
    2609.22510
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Evaluated models
    Llama-3.1-8B-Instruct, Llama-3.1-70B-Instruct, Qwen2.5-32B-Instruct and others15
    Abstract论文揭示了条件触发使提示注入绕过防御并在触发时执行工具，提出轻量检测器并在摄入期有效防范。

    论文针对大语言模型智能体面临的间接提示注入威胁，研究了利用条件句式实现时间分离的爆炸提示词。

    Paper analysisRead analysis
You have reached the end