Skip to content

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

Oct 13 · Tuesday

All papers

Found 10 papers
Filter6

Attack type

Jailbreaks24Prompt injection58Poisoning and backdoors68Model tampering15Extraction and theft20Detection evasion10Malicious use9

Attack technique

Defense-targeted5

Defense type

Model hardening4Detection and filtering4

Impact

Output manipulation4

System type

Models and APIs8LLM applications12AI Agent10coding agent2web agent0

Attacker access

Black-box3White-box4

Attack surface / entry point

Images, audio and video5

Layer

Prompt layer21Model layer23Application layer2Training and data layer8

System component

Guardrails and judges4Vision3Multimodal3
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 227papers have no tags yet and are not included in filtered results.
Attack type：Detection evasionSystem type：Models and APIsSystem type：coding agentSystem type：web agentLayer：Application layerLayer：Training and data layerClear all

Another 227papers do not have category tags yet and are not included in filtered results.

  1. AttacksarXiv 2610.10612

    PyCache Trap 利用 Python 缓存替换绕过七款 Agent Skill 扫描器

    提出 PyCache Trap，用字节码缓存替换绕过 Agent 技能扫描器

    arXiv
    2610.10612
    Published
    Layer
    Application layer
    Setting
    coding agent
    Evaluated models
    CISCO, HSS, AUDITOR and others8
    Abstract论文剖析智能体技能审查与执行脱节盲区，提出 PyCache Trap 攻击并构建基于可信复现的 EAV 防御。

    这篇论文研究了智能体技能（Agent Skills）安全扫描中的“审查–执行脱节”问题，并提出了对应的攻击验证与防御方案。

    Paper analysisRead analysis
  2. Analysis and theoryarXiv 2609.33898

    研究揭示训练效率与模型脆弱性的权衡：高效训练更易受对抗与隐私攻击

    比较高效与高成本训练的对抗和隐私脆弱性并分析损失几何

    arXiv
    2609.33898
    Published
    Layer
    Training and data layer
    Setting
    Models and APIs
    Evaluated models
    ResNet-18, Swin Transformer, Qwen2.5-Math-7B-Instruct and others7
    Abstract效用匹配下，三种高效训练都伴随更高的隐私与对抗脆弱性及更尖的损失几何。

    作者在视觉分类和数学推理语言模型上，检查用更少数据或更简对齐换取训练效率时，安全性质是否一起变化。比较在任务效用接近的前提下进行。视觉侧用 KNN-Shapley 的高重要性小子集对照低重要性大子集，并用预训练微调对照从头训练。

    Paper analysisRead analysis
  3. AttacksarXiv 2609.27124

    Fed-ADR：用恶意编排服务器协同客户端梯度操纵攻击联邦学习

    提出 Fed-ADR，用编排服务器协同操纵梯度攻破联邦学习并检测恢复

    arXiv
    2609.27124
    Published
    Layer
    Training and data layer
    Setting
    Models and APIs
    Attacker
    Gray-box
    Evaluated models
    CNN（MNIST：2 Conv + 3 FC）, CNN（Fashion-MNIST：6 Conv + 1 FC）, ResNet18（CIFAR-10）
    AbstractFed-ADR 用 gray-box 编排攻击绕过多种聚合防御，再用 Hessian 一致性检测和窗口内恢复把准确率拉回。

    Fed-ADR 是一套面向联邦学习的攻击、检测与恢复框架：编排服务器改写合谋客户端的梯度，使参数服务器的现有防御把投毒更新当成良性，同时在发现后用历史梯度把全局模型原地修回来。

    Paper analysisRead analysis
  4. DefensesarXiv 2609.23596

    StyleAT：用对抗训练防御人脸识别的语义攻击

    提出 BoundStyle 与 StyleAT，对抗训练防御人脸识别语义攻击

    arXiv
    2609.23596
    Published
    Layer
    Training and data layer
    Setting
    Models and APIs
    Attacker
    White-box, Black-box
    Evaluated models
    MobileFaceNet (MobileFace), ResNet (ResNet-152, IR-SE), RepVGG and others7
    AbstractBoundStyle 用 StyleGAN3 有界潜编辑快速攻击 FR。

    StyleAT 用可调的 StyleGAN3 潜空间攻击 BoundStyle 对人脸识别做对抗训练，以抵抗一般语义编辑，并在评测中面对训练时未见的 DiffPrivate。

    Paper analysisRead analysis
  5. DefensesarXiv 2608.12876

    SPARED：用对抗编辑数据训练基于推理的 AI 生成图像检测器

    提出 SPARED，用对抗编辑数据训练基于推理的 AI 生成图像检测器

    arXiv
    2608.12876
    Published
    Layer
    Training and data layer
    Setting
    Models and APIs
    Attacker
    Black-box, White-box
    Evaluated models
    Qwen3.5-9B
    AbstractSPARED 用防捷径的编辑对抗环训练 9B 推理检测器。

    SPARED 是一套用于可解释 AI 生成图像检测的攻防强化学习流程，报告模型是 Qwen3.5-9B 上的第三轮防御器。

    Paper analysisRead analysis
  6. AttacksarXiv 2608.09732

    ColluSkill 用跨技能组合绕过 Agent 技能扫描器

    提出 ColluSkill，用跨技能组合绕过 Agent 技能扫描器

    arXiv
    2608.09732
    Published
    Layer
    Application layer
    Setting
    coding agent
    Attacker
    Black-box, Gray-box
    Evaluated models
    GPT-5.5, DeepSeek-V4-Pro, GLM-5.2

    Abstract论文揭示了单技能孤立扫描的盲区，提出多技能链攻击 ColluSkill 与上下文防御 ChainGuard 并验证了有效性。

    Paper analysisRead analysis
  8. DefensesarXiv 2602.18252

    Adversarial robustness of discrete image tokenizers

    提出无监督对抗微调，加固离散图像 tokenizer

    arXiv
    2602.18252
    Published
    Layer
    Training and data layer
    Setting
    Models and APIs
    Evaluated models
    UniTok, UniTok-MLLM, TiTok-BL128 and others7
    Abstract无监督嵌入攻击暴露离散 tokenizer 的弱点，只微调 encoder 即可提升多任务鲁棒准确率。

    作者研究离散图像 tokenizer 的对抗鲁棒性，给出与任务无关的嵌入攻击，以及只微调 encoder 的无监督对抗训练。

    Paper analysisRead analysis
  9. DefensesarXiv 2602.12461

    Semantic-aware adversarial fine-tuning for CLIP

    Propose SAFT, which uses semantic description ensembles to construct adversarial examples and fine-tune the image encoder

    arXiv
    2602.12461
    Published
    Layer
    Training and data layer
    Setting
    Models and APIs
    Evaluated models
    ViT-B/32, CLIP-L/14
    AbstractSAFT fine-tunes the CLIP image encoder with ensemble adversarial examples from refined class descriptions to improve the trade-off between zero-shot accuracy and robustness.

    SAFT is a method for adversarially fine-tuning the CLIP image encoder to improve the accuracy–robustness trade-off in zero-shot classification.

    Paper analysisRead analysis
  10. AttacksarXiv 2601.14310

    CORVUS：用 LoRA 伪装内部信号绕过单次幻觉检测器

    提出 CORVUS，用 LoRA 伪装内部遥测以绕过幻觉检测器

    arXiv
    2601.14310
    Published
    Layer
    Training and data layer
    Setting
    Models and APIs
    Attacker
    White-box
    Evaluated models
    Llama-2-7B-Chat, Vicuna-7B (v1.5), Llama-3-8B-Instruct and others4

    Abstract作者称内部遥测在自适应模型侧对抗下易被操纵，CORVUS 通过轻量适配器微调降低了多种幻觉检测器的效果。

    Paper analysisRead analysis
You have reached the end