Skip to content

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

Oct 12 · Monday

All papers

Found 2 papers
Filter3

Attack type

Jailbreaks16Prompt injection2Detection evasion6

Defense type

Detection and filtering2

Layer

Prompt layer2Application layer30
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 injectionDefense type：Detection and filteringLayer：Prompt layerClear all

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

  1. Evaluation and benchmarksarXiv 2609.29429

    Jev 被用于零样本检测十类对齐失败，中位 AUROC 达 0.886

    提出 RLCDAlignBench，零样本检测多种对齐失败

    arXiv
    2609.29429
    Published
    Layer
    Prompt layer
    Setting
    Models and APIs
    Evaluated models
    Jev (jev-1.13.0)
    Abstract一次通用问题已能给多数对齐失败排序，大的误差来自状态和标签。

    RLCDAlignBench 测量用强化学习做校准决策的 Jev，能否当作对齐失败的零样本检测器。

    Paper analysisRead analysis
  2. 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