Skip to content

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

Oct 12 · Monday

All papers

Found 11 papers

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

  1. 研究评估 GradSafe 在多轮对话中的越狱检测脆弱性

    评测多轮对话中 GradSafe 越狱检测的可分性与脆弱性

    Published
    Evaluated models
    Llama 3.1 8B Instruct, Qwen2.5-7B-Instruct
    AbstractCWS 显示不安全梯度在真实多轮流量中变弱,且随攻击族和模型而变。

    作者评估梯度越狱检测从单条提示词迁到多轮对话后还剩多少可分性,方法是用 Context Window Scanner 把 GradSafe 原封不动地套到用户轮窗口上。

    Paper analysisRead analysis
  2. AttacksarXiv 2607.14493

    LogInject 框架披露 LLM 日志分析中的被动提示注入

    提出 LogInject 框架,评测日志分析中的被动提示注入及缓解

    Published
    Evaluated models
    GPT-4o, Claude 3.5 Sonnet, Llama-3-70B-Instruct

    Abstract论文评估了 LLM 日志分析中的上下文污染风险,提出分片拼接等攻击与三层防御,指出必须结合架构隔离与人工介入。

    Paper analysisRead analysis
  3. MultiTurnPSB

    构建 MultiTurnPSB,评测四轮医疗越狱与分类器输入防御

    Published
    Evaluated models
    GPT-4.1-mini, Claude Sonnet 4.5
    Abstract多轮攻击加剧医疗模型风险,分类器干预有效但受高误报率制约。

    MultiTurnPSB 针对患者端医疗大模型在持续交互中的安全风险,构建了包含三种攻击模态的四轮对抗评测基准。

    Paper analysisRead analysis
  4. ADVERSA:测量大语言模型中的多轮护栏退化与评判可靠性

    用 ADVERSA 测量多轮对抗下护栏退化与评审可靠性

    Published
    Evaluated models
    Claude Opus 4.6, Gemini 3.1 Pro, GPT-5.2
    AbstractADVERSA 用逐轮合规轨迹和三评审共识测量多轮护栏变化。

    ADVERSA是一套自动多轮红队测量框架,把护栏行为记成逐轮合规轨迹,并同时测量评审是否一致。要处理的问题是:单轮二元通过或失败既看不到持续对抗下安全属性如何变化,也分不开拒答逐步巩固和分数保持稳定。作者认为真实使用中的对手会改写并持续多轮。

    Paper analysisRead analysis
  5. AttacksarXiv 2602.07379

    Aegis: Governance, Integrity, and Security for AI Voice Agents

    提出 Aegis 红队框架,多轮攻击高风险语音 Agent

    Published
    Setting
    AI Agent
    Evaluated models
    GPT-4o, GPT-4o-mini, Gemini-1.5 Pro and others7
    AbstractAegis red-teams three types of voice agents: query-based access eliminates authentication and leakage successes, but behavioral attacks remain.

    Aegis uses multi-turn red-teaming evaluation on ALLM voice agents already integrated into business systems. The authors call this the first systematic red-teaming framework in this setting.

    Paper analysisRead analysis
  6. AttacksarXiv 2603.20198

    研究者提出 MM-Plan 多模态越狱框架

    提出 MM-Plan 多模态越狱框架,自动规划多轮图像编辑以越狱视觉独占目标

    Published
    Attacker
    Black-box
    Evaluated models
    Llama-3.2-11B, InternVL3-8B, Qwen3-VL-8B and others8
    Abstract作者称全局规划能攻破对单轮攻击更稳的前沿 MLLM。

    MM-Plan 是面向 Visual Exclusivity 的 black-box 多模态红队方法,并配有人工基准 VE-Safety。

    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