Skip to content

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

Oct 12 · Monday

All papers

Found 3 papers
Filter5

Attack type

Jailbreaks15Prompt injection3Poisoning and backdoors5Detection evasion3

Attack technique

Gradient and representation optimization3Automated search10Encoding and obfuscation5Role-play and persuasion4Defense-targeted7Dormant triggers9

Attack surface / entry point

User input3Web pages and interfaces4Code repositories and dependencies0Images, audio and video8Training data0
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 232papers have no tags yet and are not included in filtered results.
Attack type：Prompt injectionAttack technique：Gradient and representation optimizationAttack surface / entry point：User inputAttack surface / entry point：Code repositories and dependenciesAttack surface / entry point：Training dataClear all

Another 232papers do not have category tags yet and are not included in filtered results.

  2. AttacksarXiv 2610.09027

    P-VMI：对抗图像经 KV cache 持续影响多轮对话

    提出持久视觉记忆注入，使对抗图像经缓存在触发时操控输出

    arXiv
    2610.09027
    Published
    Layer
    Infrastructure layer
    Setting
    Models and APIs
    Evaluated models
    Qwen3-8B, Qwen3-VL-8B-Instruct, Gemma-4-12B

    Abstract论文提出 P-VMI，证实对抗输入被掩蔽后仍可经 KV 缓存持久控制模型，强调了保留状态的安全风险。

    Paper analysisRead analysis
You have reached the end