Skip to content

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

Oct 12 · Monday

All papers

Found 13 papers
Filter5

Attack type

Jailbreaks13Poisoning and backdoors7Detection evasion11

Attack technique

Gradient and representation optimization17Automated search42Multi-turn escalation21Encoding and obfuscation38Role-play and persuasion21Conversation structure manipulation9Reasoning-chain manipulation7Cross-modal payloads32Defense-targeted5

Impact

Harmful content13

System type

Models and APIs13AI Agent6Multi-agent systems0

Attacker access

Black-box8

Attack surface / entry point

User input13

Layer

Prompt layer11

System component

Guardrails and judges4
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 232papers have no tags yet and are not included in filtered results.
Attack type：JailbreaksAttack technique：Conversation structure manipulationAttack technique：Defense-targetedSystem type：Models and APIsSystem type：Multi-agent systemsClear all

Another 232papers do not have category tags yet and are not included in filtered results.

  1. AttacksarXiv 2610.06670

    研究者提出 Reward Stealing Attack，从对齐模型行为反推安全奖励实施攻击

    提出 ReSA，从对齐模型行为恢复安全奖励并在解码时反转

    arXiv
    2610.06670
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Attacker
    White-box, Gray-box
    Evaluated models
    Llama3.1-8B-Instruct, Gemma-7B-Instruct, Qwen2.5-7B-Instruct and others9
    AbstractReSA 用最大熵 IRL 从对齐模型行为恢复代理安全奖励，并在解码时反转以诱导有害输出。

    ReSA 是一种对抗攻击：从对齐模型的可观察行为恢复代理安全奖励，再在解码时把该奖励反过来用。。

    Paper analysisRead analysis
  2. AttacksarXiv 2609.36956

    研究者提出 Controlled Decoding Attacks，通过纯文本接口越狱黑盒 LLM

    提出 BLINDBIAS，通过纯文本续写与前缀控制越狱黑盒模型

    arXiv
    2609.36956
    Published
    Layer
    Prompt layer
    Setting
    Models and APIs
    Attacker
    Black-box
    Evaluated models
    GLM-5, Gemini-3.5-Flash, Qwen3-32B and others4
    Abstract作者认为，隐藏数值概率并不足以消除支持重复采样和前缀续写的解码攻击面。

    BLINDBIAS 是一种针对 sample-only 续写接口的 black-box 解码时越狱框架，研究没有目标数值概率时，采样能否支持逐步控制。

    Paper analysisRead analysis
  6. AttacksarXiv 2606.21077

    OTTER：仅替换五个 token 即可绕过 GPT 系列毒性审核

    提出 OTTER 词元替换越狱，绕过表面毒性审核诱导有害回答

    arXiv
    2606.21077
    Published
    Layer
    Prompt layer
    Setting
    Models and APIs
    Attacker
    Black-box
    Evaluated models
    gpt-4-turbo, gpt-4o, gpt-4o-mini and others4

    Abstract论文展示了表面毒性与恶意意图的解耦现象，通过标准 API 实现黑盒越狱测试，并提出闭环分类器加固建议。

    Paper analysisRead analysis
  7. Analysis and theoryarXiv 2606.04168

    论文提出随机插入攻击，利用自回归一致性绕过 LLM 安全对齐

    解释自回归一致性如何导致浅层安全对齐，并提出随机插入攻击

    arXiv
    2606.04168
    Published
    Layer
    Prompt layer
    Setting
    Models and APIs
    Abstract作者用自回归一致性串起浅层对齐、插入攻击和最坏延续对齐。

    作者把浅层安全对齐和一类续写攻击都归到自回归一致性上。

    Paper analysisRead analysis
  8. 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
  12. AttacksarXiv 2510.10271

    MetaBreak：通过特殊 token 操纵越狱在线 LLM 服务

    提出 MetaBreak，用特殊 token 操纵越狱在线 LLM 服务并绕过审核

    arXiv
    2510.10271
    Published
    Layer
    Prompt layer
    Setting
    Models and APIs
    Attacker
    Black-box
    Evaluated models
    Llama-3.3-70B-Instruct, Qwen-2.5-72B-Instruct, Gemma-2-27B-Instruct and others10

    Abstract利用特殊 token 注入对抗平台模板包裹与审核，多场景验证了越狱有效性与互补性。

    Paper analysisRead analysis
You have reached the end