Skip to content
Oct 13 · Tuesday

All papers

Found 2 papers
Filter4

Attack technique

Gradient and representation optimization14Automated search4Multi-turn escalation0Conversation structure manipulation2Defense-targeted16Dormant triggers24

Layer

Prompt layer30Model layer1Application layer12Training and data layer1
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 213papers have no tags yet and are not included in filtered results.
Attack technique：Multi-turn escalationAttack technique：Conversation structure manipulationLayer：Model layerLayer：Training and data layerClear all

Another 213papers do not have category tags yet and are not included in filtered results.

  1. AttacksarXiv 2610.12644

    Cancerous backdoor attack: progressive activation via invisible tokens and a stage controller.

    Proposes the Cancerous backdoor, which progressively corrupts reasoning using invisible stage tokens.

    arXiv
    2610.12644
    Published
    Layer
    Training and data layer
    Setting
    Models and APIs
    Evaluated models
    Llama-3.1-8B-Instruct, Qwen2.5-7B-Instruct, Mistral-7B-Instruct-v0.3
    AbstractHidden tokens plus a stage controller make the backdoor progressively corrupt reasoning upon triggering, and the authors believe that looking only at the answer will miss it.

    Cancerous Backdoor Attack changes LLM backdoors from one-time activation to multi-stage reasoning corruption that accumulates progressively with triggers.

    Paper analysisRead analysis
  2. InterpretabilityarXiv 2603.08234

    The Continuation vs. Refusal Debate: Mechanism Analysis of Continuation-Triggered Jailbreaks in Large Language Models

    Analyzing the attention head mechanism of continuation-triggered jailbreaks and proposing HCS

    arXiv
    2603.08234
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Evaluated models
    LLaMA-2-7B-Chat, Qwen2.5-7B-Instruct
    AbstractThe authors state that jailbreaks arise from competition between two types of heads, and that HCS plus distillation can use this competition for inference-time intervention.

    The authors use attention head mechanism analysis for continuation-triggered jailbreaks: under the same harmful instruction, moving the continuation suffix from after the instruction to outside the prompt boundary makes the model more likely to continue generating along the suffix.

    Paper analysisRead analysis
You have reached the end