Skip to content

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

Oct 12 · Monday

All papers

Found 15 papers
Filter5
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 233papers have no tags yet and are not included in filtered results.

Another 233papers do not have category tags yet and are not included in filtered results.

  1. 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

    Published
    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
  2. AttacksarXiv 2609.09553

    研究:任意密文攻击前沿大模型无需微调即可越狱

    提出任意字母置换密码越狱,无需微调即可诱导有害输出

    Published
    Attacker
    Black-box
    Evaluated models
    Claude Sonnet 4, Claude Sonnet 4.5, Gemini 3 Flash (preview) and others7

    Abstract前沿大模型无需微调即可通过提示词学会字母置换密码,进而绕过分类器与对齐,作者呼吁关注能力提升带来的安全风险。

    Paper analysisRead analysis
  3. 论文揭示大推理模型的对齐崩溃并提出 Reasoning Trap 越狱范式

    揭示推理加深引发的对齐坍塌,用 Reasoning Trap 放大越狱

    Published
    Evaluated models
    Qwen3-8B, Qwen3-14B, Llama2-7B and others8
    Abstract更深推理提升题目准确率,同时提高扰动下的相对损失。

    作者研究扩展推理是否以对齐稳健性为代价,提出 ALR、RT 与 RRA。。

    Paper analysisRead analysis
  4. 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

    Published
    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
  5. AttacksarXiv 2603.10091

    Multi-Stream Perturbation Attack: Breaking the Safety Alignment of Reasoning LLMs through Concurrent Task Interference

    提出多流扰动攻击,交织有害与良性任务绕过思考型 LLM 安全对齐

    Published
    Evaluated models
    Qwen3 1.7B, Qwen3 4B, Qwen3 8B and others11
    Abstract多流扰动用任务交织测试 thinking 模式,作者称它同时冲击内容安全与推理稳定性。

    多流扰动攻击把有害任务与良性任务织进同一提示词,测试 thinking 模式的内容安全与推理稳定性。作者认为,交织多任务会拉长思考,使安全检测面对被打散的有害意图,并可能把推理用于合理化,或陷入崩溃与重复。方法不访问梯度。

    Paper analysisRead analysis
  6. 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

    Published
    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
  7. 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

    Published
    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