Skip to content

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

Oct 12 · Monday

All papers

Found 30 papers
Filter4

Attack type

Prompt injection13Poisoning and backdoors8Extraction and theft10

Attack technique

Encoding and obfuscation3Defense-targeted4Dormant triggers7

Defense type

Instruction–data separation3Permissions and approval3

Impact

Harmful content34Unauthorized actions87Data and privacy leaks30Output manipulation40Availability and reliability6Oversight failure9

System type

Models and APIs13AI Agent17coding agent3

Attacker access

White-box7

Attack surface / entry point

User input61Web pages and interfaces6Documents and messages9Tool responses9Tool and skill descriptions11Code repositories and dependencies4Retrieval corpus3Memory writes9Inter-agent messages6Images, audio and video9Training data7Weights and gradients14Distribution channels8Inference services and hardware8

Layer

Model layer4Application layer17Training and data layer8

System component

MCP and skills3Memory8Permissions and sandboxing4Fine-tuning and open weights5Multimodal3
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.
Impact：Data and privacy leaksAttack surface / entry point：Tool responsesAttack surface / entry point：Memory writesAttack surface / entry point：Weights and gradientsClear all

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

  1. 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

    arXiv
    2610.07510
    Published
    Layer
    Application layer
    Setting
    coding agent
    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
  2. AttacksarXiv 2610.05601

    Tracer 框架可从遗忘后的扩散模型中识别被擦除概念

    提出 TRACER，从权重差识别扩散模型被擦除概念

    arXiv
    2610.05601
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Attacker
    White-box
    Evaluated models
    Stable Diffusion v1.5, Stable Diffusion 3, FLUX.1 and others5
    AbstractTRACER 用权重足迹识别未披露擦除概念并估计个数，作者称数秒内完成且准确率高于对照。

    TRACER 针对的是遗忘扩散模型上的目标识别：提供者从公开基座 W 用已发表方法擦掉未知集合 S⋆，只发布 W′。攻击者还有假定包含这些概念的词表，但不知擦了谁、擦了几个、用了什么算法。

    Paper analysisRead analysis
  3. AttacksarXiv 2610.05453

    研究者提出 Privacy-Leaking Watermarks，可在本地多模态模型中泄露对话隐私

    提出 PLW，用微调把先前对话敏感触发编码进后续生成图像

    arXiv
    2610.05453
    Published
    Layer
    Training and data layer
    Setting
    Models and APIs
    Evaluated models
    OmniGen2, BAGEL-7B

    AbstractPLW 把先前对话线索写成后续图像中的隐水印，检出随触发、模型和间隔变化。

    Paper analysisRead analysis
  4. AttacksarXiv 2610.04589

    StegoMemory red team testing: agent persistent memory can be used as a cross-session covert channel

    提出 StegoMemory，评测智能体持久记忆作为跨会话隐写信道

    arXiv
    2610.04589
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Evaluated models
    Llama 3.1 405B, Claude 3.5 Sonnet, GPT-4o and others13

    Abstract研究揭示智能体持久记忆可作为隐蔽信道跨会话传输机密，写入持久化是主要防御瓶颈，呼吁建立记忆完整性防御。

    Paper analysisRead analysis
  6. AttacksarXiv 2610.04128

    研究显示拆分学习中的梯度可提升客户端文本重建率

    衡量分裂学习中梯度相对激活对客户文本重建的额外贡献

    arXiv
    2610.04128
    Published
    Layer
    Training and data layer
    Setting
    Models and APIs
    Evaluated models
    GPT-2 (openai-community/gpt2, 124M), Qwen3-0.6B
    Abstract激活已恢复大部分 token。

    这篇工作测量 split learning 分裂点上的文本泄漏：激活单独能恢复多少，训练回传的梯度再增加多少，以及按 token 还是按整篇计分会不会改写结论。

    Paper analysisRead analysis
  7. AttacksarXiv 2610.01365

    ReGap：无需真实隐私数据即可通过微调重新提取模型隐私关联

    提出 ReGap，用自生成伪监督微调恢复模型中的隐私关联

    arXiv
    2610.01365
    Published
    Layer
    Training and data layer
    Setting
    Models and APIs
    Attacker
    White-box, Gray-box
    Evaluated models
    GPT-2 Small, GPT-2 Medium, GPT-2 Large and others6

    Abstract提出无真实私有监督的恢复攻击 ReGap，实验显示微调可通过自生成数据唤醒模型潜在隐私关联，突显后适应隐私风险。

    Paper analysisRead analysis
  9. DefensesarXiv 2610.00371

    FlowReview：以授权配对评测控制多智能体组合信息流

    提出 FlowReview，用授权配对与确定性提交门控控制多智能体组合信息流

    arXiv
    2610.00371
    Published
    Layer
    Application layer
    Setting
    Multi-agent systems
    Evaluated models
    Sonnet 4.5, Haiku 4.5, Qwen3-32B and others5
    Abstract配对标准要求拒绝禁止使用并完成授权使用，FlowReview 把三项审查接到执行。

    这篇工作把多智能体安全写成一件必须同时成立的事：拦住组合信息所启用的禁止使用，并完成同一场景里任务所需的授权使用。

    Paper analysisRead analysis
  11. DefensesarXiv 2609.33371

    论文提出保险库中介执行边界，评估 LLM Agent 的 API 凭据处理风险

    提出并评测保险库中介执行边界，隔离 Agent 的 API 凭据

    arXiv
    2609.33371
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Evaluated models
    Corvic Security Vault
    Abstract作者称，凭据分离可减少披露路径，但权限、操作授权和配置验证仍需独立控制。

    这是一项智能体 API 凭据威胁分析及 Vault 执行边界的功能评测。作者关心的不是模型能否承诺保密，而是认证材料是否会进入模型、日志、记忆和执行代码。

    Paper analysisRead analysis
  12. AttacksarXiv 2609.27542

    Researchers use control token injection to delete gpt-oss-20b's reasoning chain and bypass chain-of-thought monitoring

    提出控制标记注入，清空工具 Agent 的思维链以绕过推理监控

    arXiv
    2609.27542
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Evaluated models
    openai/gpt-oss-20b, google/gemma-4-26B-A4B-it, deepseek-ai/DeepSeek-R1-Distill-Qwen-7B and others4

    Abstract论文阐明控制标记注入可抑制 CoT 使监控失效并促成拒绝绕过，且工具执行受解析器宽容度影响。

    Paper analysisRead analysis
  14. DefensesarXiv 2609.20532

    面向旧款 GPU 的可验证差分隐私训练框架：用 CPU 侧 TEE 校验 GPU 梯度

    AI summary论文提出一种在旧款 GPU 上实现可验证差分隐私（DP）训练的框架，用 CPU 侧 TEE 配合不受信任的 GPU 完成校验。

    arXiv
    2609.20532
    Published
    Layer
    Training and data layer
    Setting
    Models and APIs
    Evaluated models
    5-layer MLP, WideResNet, GPT-2-medium and others4
    AbstractCPU TEE 概率抽查不可信 GPU 上的 DP-SGD，以小开销约束频繁偏离。

    TEE-Certified DP 用已部署的 CPU TEE 监视不可信旧 GPU 上的 DP-SGD，使监管方能在不看训练数据的情况下检查声明的隐私机制是否被执行。

    Paper analysisRead analysis
  15. AttacksarXiv 2609.18217

    研究：跨通道碎片化攻击可绕过 MCP 单通道防御

    提出跨通道分段攻击，利用 MCP 隐式信任外发敏感文件

    arXiv
    2609.18217
    Published
    Layer
    Application layer
    Setting
    coding agent
    Evaluated models
    GPT-4o, GPT-4o-mini, GPT-5.4 and others15

    Abstract论文揭示了 MCP 多通道隐式信任层级，通过跨通道分段与协议级利用突破现有防御，展示了严重的凭证外发风险。

    Paper analysisRead analysis
  17. DefensesarXiv 2609.15671

    QPriv-VL：面向视觉语言模型的问题引导 token 裁剪隐私防御

    提出 QPriv-VL，用问题引导剪枝降低分布式视觉问答的隐私泄露

    arXiv
    2609.15671
    Published
    Layer
    Training and data layer
    Setting
    Models and APIs
    Evaluated models
    LLaVA-1.5-7B, Llama-2
    AbstractQPriv-VL 在切层前按问题相关度与 DINOv2 敏感度剪视觉 token，作者称能在约四成 token 下兼顾准确率与四类攻击。

    QPriv-VL 把问题引导的视觉 token 剪枝做成分布式 VQA 的客户端隐私防御，而不是只做集中式推理加速。

    Paper analysisRead analysis
  18. AttacksarXiv 2609.10117

    研究揭示基于混淆的端侧 LLM 保护方案的安全边界

    提出 Collapse，从端侧混淆暴露视图抽取高效用替代模型

    arXiv
    2609.10117
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Evaluated models
    BERT-Base, ViT-Base, Qwen2.5-0.5B and others4
    AbstractOprior 是四原语复合的安全边界，Collapse 利用列方向泄漏抽取替代模型，Oext 只被同一攻击评测。

    这篇工作用代数原语统一若干 TEE 卸载混淆，给出该族的典范边界，再说明该边界挡不住一种分阶段模型抽取。。

    Paper analysisRead analysis
  20. DefensesarXiv 2609.04875

    Forgetting without restart: execution-state forgetting for stateful LLM agents

    Proposes execution-state forgetting, using provenance-guided selective replay to purify stateful agents

    arXiv
    2609.04875
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Evaluated models
    Llama-3.1-8B-Instruct, Qwen2.5-7B-Instruct, Mistral-7B-Instruct-v0.3
    AbstractSelective replay concatenates the clean prefix with the sanitized suffix, and main-table metrics match full reset.

    This work defines forgetting in long-horizon agents as runtime counterfactual equivalence, rather than deleting a plaintext memory.

    Paper analysisRead analysis
Load more