Skip to content

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

Oct 12 · Monday

All papers

Found 4 papers
Filter4

Attack type

Poisoning and backdoors3

Attack technique

Gradient and representation optimization12Conversation structure manipulation1Defense-targeted7Dormant triggers3Selection manipulation0

System type

Models and APIs4

Layer

Prompt layer10Model layer4Application layer49Training and data layer19
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 255papers have no tags yet and are not included in filtered results.
Attack technique：Conversation structure manipulationAttack technique：Dormant triggersAttack technique：Selection manipulationLayer：Model layerClear all

Another 255papers do not have category tags yet and are not included in filtered results.

  1. AttacksarXiv 2610.13928

    AI models can provably hide arbitrary capabilities

    Proposes digital lock compilation, encrypting executable networks into host weights to hide arbitrary capabilities

    arXiv
    2610.13928
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Evaluated models
    Gemma 3 270M
    AbstractThe authors use a digital lock to hide an executable capability and state that elicitation on the chemistry and parity tasks did not recover the capability.

    The authors construct a class of backdoors that encrypt an executable network into the weights, used to discuss the limits of white-box elicitation audits under supply chain attacks.

    Paper analysisRead analysis
  2. AttacksarXiv 2610.06049

    研究者提出仅修改 SAE 解码器的后门攻击，可在不改动语言模型的情况下植入行为

    提出只改 SAE 解码器的后门，在冻结语言模型上植入代码插入

    arXiv
    2610.06049
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Evaluated models
    Gemma 3 4B Instruct, Qwen3 1.7B, Llama 3.1 8B Instruct
    Abstract只改解码器的 SAE 可带上代码插入后门，且若干常规质量指标变化不大。

    只改 SAE 解码器、冻结编码器与语言模型，即可把代码插入行为放进推理时的辅助组件。作者把这视为 SAE 供应链问题：checkpoint 一旦替换某一层激活，就参与后续计算，而不只是解释工具。

    Paper analysisRead analysis
  4. InterpretabilityarXiv 2603.08234

    续写与拒答之争：大语言模型中续写触发越狱的机制分析

    分析续写触发越狱的注意力头机制并提出 HCS

    arXiv
    2603.08234
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Evaluated models
    LLaMA-2-7B-Chat, Qwen2.5-7B-Instruct
    Abstract作者称越狱来自两类头竞争，HCS 加蒸馏可把该竞争用于推理时干预。

    作者用注意力头机制分析 continuation-triggered jailbreak：同一有害指令下，把 continuation 后缀从指令后面挪到提示词边界外，模型更容易顺着后缀继续生成。

    Paper analysisRead analysis
You have reached the end