Skip to content

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

Oct 12 · Monday

All papers

Found 172 papers
Filter2

Attack type

Jailbreaks132Prompt injection93Poisoning and backdoors88Model tampering16Extraction and theft40Detection evasion41Denial of service8Malicious use3

Attack technique

Gradient and representation optimization26Automated search56Multi-turn escalation22Encoding and obfuscation34Role-play and persuasion19Conversation structure manipulation8Reasoning-chain manipulation8Cross-modal payloads35Defense-targeted26Dormant triggers3

Defense type

Model hardening5Detection and filtering6Permissions and approval3

Impact

Harmful content118Unauthorized actions12Data and privacy leaks4Output manipulation28Availability and reliability3Oversight failure6

System type

Models and APIs137LLM applications11AI Agent25coding agent7

Attacker access

Black-box107Gray-box9White-box24No-box (offline transfer)4

Attack surface / entry point

User input140Documents and messages3Tool responses8Tool and skill descriptions8Images, audio and video46Training data4Weights and gradients11Distribution channels3Inference services and hardware3

Layer

Prompt layer117Model layer18Application layer32Training and data layer4

System component

MCP and skills5Guardrails and judges40Monitors4Reasoning chains10Fine-tuning and open weights4Vision30Audio7Image generation16Multimodal53
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 265papers have no tags yet and are not included in filtered results.
Attack type：JailbreaksAttack type：Detection evasionClear all

Another 265papers do not have category tags yet and are not included in filtered results.

  1. AttacksarXiv 2610.12292

    The paper proposes an option channel attack: changing one option label can make an agent guardrail allow a prohibited operation

    Proposing an option channel attack that renames option labels so that agent guardrails allow prohibited operations

    arXiv
    2610.12292
    Published
    Layer
    Application layer
    Setting
    LLM applications
    Attacker
    Black-box
    Evaluated models
    LAYA-TD, LAYA-EN, LAYA-ML and others5

    AbstractThe authors' evaluation indicates that typed models should not serve as final safety arbiters; they are susceptible to off-policy text and option name manipulation, and confidence filtering cannot resist attacks.

    Paper analysisRead analysis
  2. AttacksarXiv 2610.11112

    EpiReal-Bench：商用图像生成模型虚假声明红队基准

    构建 EpiReal-Bench，评测图像生成器将虚假主张渲染为可信证据

    arXiv
    2610.11112
    Published
    Layer
    Prompt layer
    Setting
    Models and APIs
    Attacker
    Black-box
    Evaluated models
    GPT-Image-2, Nano Banana 2, Grok Imagen 2.0 and others4
    Abstract四款商用图像模型能把假主张画成可信证据。

    EpiReal-Bench 用来量商用图像生成器会不会把虚假现实主张画成可信视觉证据。

    Paper analysisRead analysis
  5. 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
  7. AttacksarXiv 2610.07323

    ATLAS：用自适应信任域与主动学习搜索潜在对抗样本集

    提出 ATLAS 用水平集估计恢复黑盒分类器的对抗输入集合

    arXiv
    2610.07323
    Published
    Layer
    Prompt layer
    Setting
    Models and APIs
    Attacker
    Black-box
    Evaluated models
    LeNet5, ResNet50 (CIFAR-10 standard), ResNet50 (ImageNet standard) and others5
    AbstractATLAS 用主动水平集估计构造黑盒对抗集，作者称其集合比单点攻击更具代表性。

    ATLAS 是一个查询式 black-box 框架，用来构造诱发失败的对抗输入集合，供鲁棒性审计使用。

    Paper analysisRead analysis
  8. AttacksarXiv 2610.07125

    PEV 攻击利用嵌入向量加噪越狱六款开源权重模型

    提出 PEV 攻击，在输入嵌入上加高斯噪声越狱开源模型

    arXiv
    2610.07125
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Evaluated models
    Llama-3.1-8B-Instruct, Qwen2.5-1.5B-Instruct, Phi-4-mini-3.8B and others6
    AbstractPEV 用 embedding 高斯噪声，在六个模型上越狱 JailbreakBench 全部提示。

    PEV 是对 open-weight LLM 的 embedding 噪声越狱。

    Paper analysisRead analysis
  9. AttacksarXiv 2610.06670

    研究者提出 Reward Stealing Attack，从对齐模型行为反推安全奖励实施攻击

    提出 ReSA，从对齐模型行为恢复安全奖励并在解码时反转

    arXiv
    2610.06670
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Attacker
    White-box, Gray-box
    Evaluated models
    Llama3.1-8B-Instruct, Gemma-7B-Instruct, Qwen2.5-7B-Instruct and others9
    AbstractReSA 用最大熵 IRL 从对齐模型行为恢复代理安全奖励，并在解码时反转以诱导有害输出。

    ReSA 是一种对抗攻击：从对齐模型的可观察行为恢复代理安全奖励，再在解码时把该奖励反过来用。。

    Paper analysisRead analysis
  10. AttacksarXiv 2610.05943

    CRIME 框架利用良性 Agent 技能组合诱发恶意行为

    提出 CRIME 框架，组合良性 Agent 技能诱发恶意行为

    arXiv
    2610.05943
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Evaluated models
    DeepSeek-V4-Flash, GPT-4o-mini, GPT-4o and others6
    Abstract良性技能经 DCA 或 ACA 组合后可产生恶意环境后果，单独审查对不上。

    CRIME 把公共技能库中各自通过审查的技能配成两两组合，看联合执行能否实现指定恶意任务。。

    Paper analysisRead analysis
  11. AttacksarXiv 2610.05346

    研究者提出序列马赛克攻击并给出防御理论

    形式化 watchman 防御以阻止序贯马赛克攻击

    arXiv
    2610.05346
    Published
    Layer
    Prompt layer
    Setting
    Models and APIs
    Evaluated models
    Qwen3.6-35B-A3B, Gemma-4-26B-A4B-it, DeepSeek-V2-Lite (16B-A2.4B)
    Abstractwatchman 理论给出零失败且有用的条件。

    这篇工作同时给出序贯马赛克防御的博弈理论，以及冻结 LLM 上的分角色自博弈训练。

    Paper analysisRead analysis
  13. AttacksarXiv 2610.03166

    LiBRA：通过双向隐空间优化实现检测感知的图像水印去除

    提出 LiBRA，在潜空间双向优化以规避图像水印双侧检测

    arXiv
    2610.03166
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Attacker
    White-box
    Evaluated models
    Stable Signature, YU1, HiDDeN and others4

    AbstractLiBRA 用双向潜空间优化规避双侧水印检测，并提高相对反转基线的保真。

    Paper analysisRead analysis
  14. AttacksarXiv 2610.02432

    论文提出 LLM 输入扰动鲁棒性度量，并发布 ASA 攻击与 AttestMCP 防护

    提出 ASA 与 AttestMCP，度量并降低 LLM 对输入序列扰动的敏感

    arXiv
    2610.02432
    Published
    Layer
    Application layer
    Setting
    LLM applications, AI Agent
    Attacker
    Black-box
    Evaluated models
    Gemma-3-27B-Instruct, Gemma-3-4B-Instruct, Llama-3.2-3B-Instruct and others12
    Paper analysisRead analysis
  15. AttacksarXiv 2610.02302

    研究者提出意图隐藏越狱的信息论框架，分析组合式攻击

    提出组合式意图隐藏越狱，按先验后验匹配选择辅助任务

    arXiv
    2610.02302
    Published
    Layer
    Prompt layer
    Setting
    Models and APIs
    Evaluated models
    Qwen3-1.7B, Qwen3-4B, Qwen3-8B and others7
    Abstract用信息论选含目标的任务组合，再看查询能否既隐藏意图又让目标被执行。

    这篇工作把组合式意图隐藏写成任务选择：有害目标必须留在 bundle 里，同时让估计的有害意图概率贴近全集先验，或降到阈值以下。

    Paper analysisRead analysis
  16. AttacksarXiv 2610.03124

    研究提出 Untag 攻击框架，使开源大模型触发标签滥用检测机制失效

    提出 UNTAG，绕过开源权重模型的 trigger-tag 滥用检测

    arXiv
    2610.03124
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Attacker
    Black-box, White-box
    Evaluated models
    Llama2 (7B), Llama3 (8B), Qwen2.5 (7B)
    Abstract作者用 UNTAG 评估 trigger-tag，认为其不能充当开放权重滥用检测的主要边界。

    UNTAG 是针对开放权重 LLM 上条件滥用检测 trigger-tag 的统一攻击评估：信号可以在解码期注入，也可以写进权重，但攻击者若能改输出或改已发布权重，检测可以失效。

    Paper analysisRead analysis
  18. AttacksarXiv 2609.39607

    Pretext 攻击绕过 NVIDIA SkillSpector 等 Agent 技能扫描器

    提出 PRETEXT 攻击，迭代改写技能文本绕过技能扫描器并让 Agent 执行木马

    arXiv
    2609.39607
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Attacker
    White-box
    Evaluated models
    glm (z-ai/glm-5.1), qwen3t (qwen/qwen3-235b-a22b-thinking-2507), gpt-oss (openai/gpt-oss-120b)
    Abstract论文提出了针对多阶段技能检测器的白盒攻击，揭示了单纯依赖大模型自适应检测的局限。

    PRETEXT 是一项针对基于“静态规则加语义大模型”的智能体技能安全检测框架的白盒攻击与协同进化评估研究。

    Paper analysisRead analysis
  20. AttacksarXiv 2609.38253

    CollageAttack: Exploiting cross-modal alignment defects for spatial text composition jailbreaks against T2I models.

    提出 CollageAttack，用空间文本碎片重组越狱文生图模型

    arXiv
    2609.38253
    Published
    Layer
    Prompt layer
    Setting
    Models and APIs
    Attacker
    Black-box
    Evaluated models
    GPT-Image-2, Doubao-Seedream-5.0-Lite, Wan2.7-Image-Pro and others5

    Abstract系统揭示 T2I 跨模态空间合成安全漏洞，证实离散无害元素可在图像层面重构有害意图并放大传播强度。

    Paper analysisRead analysis
Load more