Skip to content

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

Oct 12 · Monday

All papers

Found 38 papers

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

  1. AttacksarXiv 2610.09264

    研究者提出 PackHallu:经规则文件提示注入对编码 Agent 发起包幻觉攻击

    提出 PackHallu,经规则文件提示注入诱导编码 Agent 换用攻击者指定包

    Published
    Evaluated models
    Qwen2.5-Coder-7B, Qwen3-Coder-30B, Devstral-Small-2-24B and others19
    AbstractPackHallu 诱导规则文件换包。

    PackHallu 研究一种针对编程智能体规则文件的提示注入:让智能体在本应使用合法依赖时,改导入攻击者指定并控制的包。

    Paper analysisRead analysis
  2. AttacksarXiv 2610.07510

    PersistBD: attackers can strengthen backdoors before release so that they maintain high attack success rates even after developer SFT and RL.

    提出 PERSISTBD,发布前强化供应链后门使其经良性 SFT 与 RL 后仍外发凭据

    Published
    Evaluated models
    Qwen2.5-Coder-3B-Instruct, Qwen2.5-Coder-7B-Instruct, Qwen3-Coder-30B-A3B-Instruct
    Abstract总结了论文关于后门在 SFT/RL 中存活的发现、两因子机制、PERSISTBD 方法与核心数字。

    本文研究第三方 LLM 智能体在开发者进行良性监督微调(SFT)和强化学习(RL)后训练时的后门持久性风险。

    Paper analysisRead analysis
  3. AttacksarXiv 2610.06848

    TranScope:利用 CPU 性能计数器对 Transformer 做成员推断攻击

    提出 TRANSCOPE,用 CPU 硬件计数器推断训练集成员

    Published
    Attacker
    Black-box
    Evaluated models
    BERT (4.4M-340M), ViT (22M-307M), Pythia (70M-2.8B) and others5

    AbstractTRANSCOPE 揭示了分词器在嵌入表引发的硬件访问局部性差异,证实微架构计数器可突破恒定时间与置信度遮蔽防御。

    Paper analysisRead analysis
  4. AttacksarXiv 2610.05894

    研究者提出闭环偏见注入攻击

    提出闭环激活引导,在扩散语言模型去噪过程中注入定向偏见

    Published
    Attacker
    Gray-box
    Evaluated models
    LLaDA-8B-Instruct, Dream-v0-Instruct-7B, LLaDA-MoE-7B-A1B-Instruct

    Abstract通过去噪中间概率反馈动态调节残差流转向,证明扩散语言模型在推理服务栈中存在闭环偏见注入脆弱性。

    Paper analysisRead analysis
  5. HXAI:分布式能源系统中的分层隐私保护可解释 AI 框架

    提出 HXAI 分层隐私解释框架,本地保留细解释并只发布加噪摘要

    Published
    Evaluated models
    gradient-boosted tree regression models
    AbstractHXAI 把无噪声局部 SHAP 留在家庭内,只聚合差分隐私摘要。

    HXAI 是面向分布式能源系统的分层隐私保护解释框架,服务规划、监测与诊断,而不是实时控制。

    Paper analysisRead analysis
  6. 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
  7. pikit:面向间接提示注入研究与评测的可组合工具包

    构建可组合工具包 pikit,评测编码智能体的间接提示注入

    Published
    Abstractpikit 提供组合式间接注入评测。

    pikit 是面向间接提示注入研究的组合式工具包,主要贡献是组织攻击、投递通道、防御和判定流程,而非提出新的攻击优化算法。

    Paper analysisRead analysis
  8. DefensesarXiv 2609.35659

    Tracekit:面向自主编码 Agent 的防篡改意图-推理-动作审计系统

    提出 Tracekit,审计编码 Agent 的意图、推理与动作并检测账本篡改

    Published
    Evaluated models
    Claude Code (claude -p, version 2.1), 独立评审(同一 CLI,无工具)
    AbstractTracekit 把意图、自述和动作写入可锚定的哈希链。

    Tracekit 是无第三方依赖的编码智能体审计层:把人类请求、模型自述和已执行动作并排写入可外部锚定的哈希链,执行前用正则门,事后用规则和独立模型互查。

    Paper analysisRead analysis
  9. Cave-Bench:虚假指控下 LLM 智能体最高 60.06% 的运行会破坏正确工作

    提出 CAVE-BENCH,评测智能体在虚假指责下破坏已完成的正确工作

    Published
    Evaluated models
    Claude-Sonnet-5, Claude-Opus-5, GPT-5.6-Sol and others14

    Abstract论文提出了评估智能体在虚假指责下破坏已有正确成果的 CAVE-BENCH,发现强模型易推翻已知证据,提出了门控缓解方案。

    Paper analysisRead analysis
  10. DefensesarXiv 2608.25431

    GIFT: Enforcing User Data Isolation in LLM Serving via GPU Information Flow Tracking

    Propose GIFT, isolating user data in shared LLM serving using encryption and GPU information flow tracking

    Published
    Evaluated models
    Qwen2.5-14B, Qwen2.5-32B, Qwen2.5-72B and others6
    AbstractGIFT uses cryptographic isolation plus GPU information flow rules to enforce user data isolation on vLLM and DistServe, and reports throughput overhead.

    GIFT is the authors' user data isolation system for shared LLM serving, with GIFT-CC enabling confidential computing. In the conclusion, the authors state it is the first IFT design for this scenario.

    Paper analysisRead analysis
  11. AttacksarXiv 2608.17485

    KeyPooling: Measuring where LLM API relay paths break prompt cache isolation

    Proposing KeyPooling to measure where API relays break prompt cache isolation

    Published
    Evaluated models
    grok-4-fast-non-reasoning, grok-4-1-fast-non-reasoning, grok-3 and others11
    AbstractShared upstream credentials place relay customers in the same cache domain; preserving identity or separate principals can separate them.

    KeyPooling measures where LLM API relays drop customer identity, causing prompt caches to no longer be isolated per downstream customer.

    Paper analysisRead analysis