Skip to content

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

Oct 12 · Monday

All papers

Found 3 papers
Filter4

Attack type

Jailbreaks47Prompt injection33Poisoning and backdoors27Extraction and theft3Detection evasion21

Attack technique

Automated search6Encoding and obfuscation2Role-play and persuasion3Side channels4Defense-targeted1Selection manipulation0

Impact

Data and privacy leaks3

System type

Models and APIs3
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 type：Extraction and theftAttack technique：Encoding and obfuscationAttack technique：Defense-targetedAttack technique：Selection manipulationClear all

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

  1. AttacksarXiv 2609.10117

    研究揭示基于混淆的端侧 LLM 保护方案的安全边界

    提出 Collapse，从端侧混淆暴露视图抽取高效用替代模型

    arXiv
    2609.10117
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Evaluated models
    BERT-Base, ViT-Base, Qwen2.5-0.5B and others4
    AbstractOprior 是四原语复合的安全边界，Collapse 利用列方向泄漏抽取替代模型，Oext 只被同一攻击评测。

    这篇工作用代数原语统一若干 TEE 卸载混淆，给出该族的典范边界，再说明该边界挡不住一种分阶段模型抽取。。

    Paper analysisRead analysis
  2. AttacksarXiv 2604.01039

    Evaluating and hardening LLM system instructions against encoding attack extraction

    Extract system instructions with encoding and structured requests, and harden them by rewriting with CoT

    arXiv
    2604.01039
    Published
    Layer
    Prompt layer
    Setting
    Models and APIs
    Attacker
    Black-box
    Evaluated models
    GPT-4.1-mini, GPT-3.5-turbo, Gemini-2.5-flash and others7
    AbstractEncoded requests can elicit system instructions after a direct refusal.

    This work evaluates and hardens the confidentiality of LLM system instructions under encoded extraction. The authors are concerned with: when direct extraction has been rejected, whether the model still surrenders protected content when the same request is rewritten as a formatting or encoding task.

    Paper analysisRead analysis
  3. AttacksarXiv 2601.01296

    Aggressive compression enables LLM weight stealing

    提出面向渗出的权重压缩，评估推理服务器权重窃取可行性

    arXiv
    2601.01296
    Published
    Layer
    Infrastructure layer
    Setting
    Models and APIs
    Attacker
    White-box
    Evaluated models
    Qwen2-1.5B, Qwen2-7B, Qwen2.5-1.5B and others8
    Abstract作者用残差量化加微调压缩权重，并称法医水印便宜且微调后仍可解码。

    这篇工作把 LLM 权重渗出看成 APT：攻击者已有未加密权重，但必须把完整权重藏进推理 API 的合法输出。作者认为可压缩性是被忽略的因素，因为推理量化要求解压后仍能低开销前向，而偷权重的人可以接受事后微调。

    Paper analysisRead analysis
You have reached the end