Skip to content

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

Oct 12 · Monday

All papers

Found 1 paper
Filter3

Attack type

Jailbreaks191Prompt injection1Poisoning and backdoors5Model tampering24Detection evasion3Malicious use6

Impact

Harmful content1Output manipulation10

System type

Models and APIs1AI Agent7
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 265papers have no tags yet and are not included in filtered results.
Attack type：Prompt injectionImpact：Harmful contentSystem type：Models and APIsClear all

Another 265papers do not have category tags yet and are not included in filtered results.

  1. DefensesarXiv 2609.01046

    HiveTraceGuard-Pro：面向提示注入、越狱与对抗混淆的紧凑生成式护栏

    提出生成式护栏 HiveTraceGuard-Pro，检测提示注入、越狱与混淆

    arXiv
    2609.01046
    Published
    Layer
    Prompt layer
    Setting
    Models and APIs
    Evaluated models
    HiveTraceGuard-Pro (0.6B)
    Abstract0.6B 俄英护栏在自建俄语干净集和 PI-RU 上得分最高，聚合 key 居第三，过阻断和回复精度仍是作者标出的短板。

    HiveTraceGuard-Pro 是面向请求与回复审核的 0.6B 生成式护栏，由 Qwen3-0.6B 经 LoRA 微调，在俄语和英语上训练，只输出一个 safe/unsafe 裁决。

    Paper analysisRead analysis
You have reached the end