Skip to content

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

Oct 12 · Monday

All papers

Found 25 papers
Filter5
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.

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

  1. AttacksarXiv 2610.06093

    研究评测训练数据提取风险的跨语言迁移

    用翻译前缀做跨语言训练数据提取,恢复英语训练文本中的 PII

    Published
    Evaluated models
    GPT-Neo 1.3B, GPT-Neo 2.7B, GPT-J 6B and others7
    Abstract跨语言 TDE 能恢复英语记忆的 PII,转移随多语训练和措辞保真变化。

    这篇工作检验训练数据抽取是否跨语言:英语段落里记住的 PII,能否被其他语言的前缀逐字抽出。

    Paper analysisRead analysis
  2. AgentDoxx:联网搜索 Agent 对匿名访谈文本的再识别评测

    构建 AGENTDOXX 基准,评测联网搜索 Agent 对匿名访谈的再识别

    Published
    Setting
    web agent
    Evaluated models
    GPT-5.6 Terra, GPT-5 Mini, GPT-4.1 Mini and others10

    Abstract论文提出了已知身份的重识别基准 AGENTDOXX,揭示搜索与记忆双重风险及现有防御在检索轨迹中的泄露漏洞。

    Paper analysisRead analysis
  3. AttacksarXiv 2610.01768

    LLMLeak:借 LLM 合法网页抓取实施隐蔽数据外泄

    提出 LLMLeak,借合法网页抓取把 URL 中的秘密隐蔽外传

    Published
    Evaluated models
    Meta-Llama-3.3-70B-Instruct, Meta-Llama-4-Scout-17B-16E-Instruct, Meta-Llama-3.1-8B-Instruct and others18
    Abstract作者称第三方外传可发生于正常网页获取,防护需考虑工具请求而不只考虑提示注入。

    LLMLeak 是利用网页获取请求携带预先编码秘密的隐蔽通道攻击。它关注恶意软件已能读取数据、却因网络限制或监控无法直接外传的情形。

    Paper analysisRead analysis
  4. AttacksarXiv 2609.14649

    CIG-MIA:利用上下文信息增益对 RAG 系统发起成员推断攻击

    提出 CIG-MIA,用上下文信息增益推断 RAG 知识库成员身份

    Published
    Evaluated models
    Llama-3.1-8B-Instruct, Mistral-7B-Instruct-v0.3, Llama-2-13b-chat-hf and others6
    AbstractCIG-MIA 用注入前后的答案似然差推断 RAG 库成员,灰盒可分性高于所列基线。

    CIG-MIA 是针对 RAG 外部知识库的成员推断攻击,同时覆盖灰盒和纯文本黑盒。

    Paper analysisRead analysis
  5. AttacksarXiv 2609.12448

    GraphProfiler 用个人知识图谱推断敏感属性并溯源到具体帖子

    提出 GraphProfiler,用个人知识图谱从帖子历史推断敏感属性并溯源

    Published
    AbstractGraphProfiler 用源链接个人知识图谱做属性推断,准确率接近文本基线,并把证据定位到少量源帖。

    GraphProfiler 是一个可审计的 LLM 敏感属性画像器:用源链接个人知识图谱,把推断落到具体帖子。

    Paper analysisRead analysis
  6. DefensesarXiv 2609.04767

    SHAQ: Privacy-preserving retrieval in vector databases using shadow queries

    Proposes SHAQ, which replaces document embeddings with shadow query embeddings to defend against embedding inversion.

    Published
    Attacker
    Black-box
    Evaluated models
    GTR-T5 encoder, DPR
    AbstractSHAQ replaces document embeddings with shadow query embeddings.

    SHAQ is a defense against EIA for cloud vector databases: instead of directly modifying document embeddings, it replaces them with shadow query embeddings.

    Paper analysisRead analysis
  7. DefensesarXiv 2609.01677

    Skill-as-API:面向智能体软件工程的机密多智能体协作协议

    提出 Skill-as-API,隔离多智能体协作中的 skill 正文与系统提示词

    Published
    Abstract协议把 skill 正文留在所有者侧,四层限制发现内容、权限期限和注入拼接。

    Skill-as-API 是面向智能体软件工程的协调协议,用来在跨组织调用时把 skill 的代码和系统提示词留在所有者进程。作者针对三条威胁:经通道或命名空间抽取专有方法,用注入让被调用模型输出系统提示词,以及协作结束后权限继续保留。

    Paper analysisRead analysis
  8. AttacksarXiv 2608.09867

    Researchers steal proprietary LLM inference chains via cross-model compatibility of encrypted inference blocks

    利用加密思维块的跨模型重放,诱导弱模型逐字转写专有推理链

    Published
    Attacker
    Black-box
    Evaluated models
    Claude Opus 4.8, Claude Sonnet 4.6, Claude Haiku 4.5 and others13

    Abstract论文揭示了客户端加密思维块跨模型互换漏洞,提出了低成本提取方法并给出防御方案。

    Paper analysisRead analysis
  9. AttacksarXiv 2608.04192

    研究者提出 SkillClone,仅凭正常提问即可克隆 LLM Agent 隐藏技能功能

    提出 SkillClone,仅凭良性任务交互重构闭源 Agent 技能

    Published
    Setting
    AI Agent
    Attacker
    Black-box
    Evaluated models
    DeepSeek-Flash, DeepSeek-Pro, GLM-5.1 and others5
    Abstract论文揭示了仅靠良性任务交互即可重构闭源智能体技能隐藏功能的风险,表明功能保密需要限制累积信息泄露。

    论文从功能保密视角系统研究了大语言模型智能体技能的行为重构威胁。

    Paper analysisRead analysis
  10. AttacksarXiv 2607.25560

    SigLeak 可从执行轨迹推断专有 Agent 技能

    提出 SigLeak,从黑盒 Agent 执行轨迹推断专有技能

    Published
    Setting
    AI Agent
    Attacker
    Black-box
    Evaluated models
    GPT-5.4-mini, GPT-5.5, GLM-5.2 and others4

    Abstract提出了通过良性查询和对照轨迹推断黑盒专有技能的 SigLeak 框架,揭示了智能体执行可见性带来的行为侧信道泄露风险。

    Paper analysisRead analysis
  11. AttacksarXiv 2607.01276

    研究者提出嵌入推断攻击 EIA,可在黑盒 IR 系统中识别所用嵌入模型

    提出嵌入推断攻击 EIA,在黑盒 IR 中识别所用嵌入模型

    Published
    Attacker
    Black-box
    Evaluated models
    e5-small, e5-small-v2, e5-base and others19
    AbstractEIA 用无序文档集的差异从候选中识别嵌入模型,并给出 reranker 与阈值下的计数。

    EIA 是在黑盒 IR 上识别所用嵌入模型的攻击。。

    Paper analysisRead analysis
  12. DefensesarXiv 2606.18673

    Understanding and mitigating prompt leakage attacks in real-world LLM applications

    Propose soft prompt defense AREA, re-anchoring attention to mitigate system prompt leakage

    Published
    Attacker
    Black-box
    Evaluated models
    Llama-2-7B-chat-hf, Llama-3.1-8B-Instruct, Mistral-7B-Instruct-v0.3 and others8
    AbstractThe authors measure commercial prompt leakage, propose attention drift, and use AREA to strike a trade-off between usability and leakage resistance.

    The authors study system prompt leakage in real LLM applications and propose AREA, a mitigation method that does not modify weights.

    Paper analysisRead analysis
  13. DefensesarXiv 2605.19847

    论文揭示多租户 RAG 账号合谋使隐私泄露随账号数线性增长

    提出零知识审计协议,核验多租户 RAG 的合谋差分隐私

    Published
    Abstract揭示多租户 RAG 合谋泄露按根号 k 放大,提出带零知识证明的无泄露审计协议。

    论文针对多租户 RAG 服务在多账户协同攻击下隐私边界失效的问题展开研究。

    Paper analysisRead analysis
  14. AttacksarXiv 2604.01039

    Evaluating and hardening LLM system instructions against encoding attack extraction

    Extract system instructions with encoding and structured requests, and harden them by rewriting with CoT

    Published
    Attacker
    Black-box
    Evaluated models
    GPT-4.1-mini, GPT-3.5-turbo, Gemini-2.5-flash and others7
    AbstractEncoded requests can elicit system instructions after a direct refusal.

    This work evaluates and hardens the confidentiality of LLM system instructions under encoded extraction. The authors are concerned with: when direct extraction has been rejected, whether the model still surrenders protected content when the same request is rewritten as a formatting or encoding task.

    Paper analysisRead analysis