Skip to content

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

Oct 13 · Tuesday

All papers

Found 13 papers
Filter5

Attack type

Jailbreaks13Prompt injection3Extraction and theft5Detection evasion3

Attack technique

Reasoning-chain manipulation6

Impact

Harmful content13

System type

Models and APIs13AI Agent3coding agent0Embodied systems and robotics0

Attacker access

Black-box5

Attack surface / entry point

User input13Images, audio and video4

Layer

Prompt layer8Model layer3

System component

Guardrails and judges44Monitors8Reasoning chains13Fine-tuning and open weights3Vision35Audio11Image generation15Multimodal60
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 215papers have no tags yet and are not included in filtered results.
Attack type：JailbreaksSystem type：Models and APIsSystem type：coding agentSystem type：Embodied systems and roboticsSystem component：Reasoning chainsClear all

Another 215papers do not have category tags yet and are not included in filtered results.

  2. DefensesarXiv 2609.36562

    ThinkingGuard：通过逐步风险归因解码多模态大语言模型中的隐式危害

    构建 TriggerBench 并训练 ThinkingGuard，检测图文隐式风险

    arXiv
    2609.36562
    Published
    Layer
    Prompt layer
    Setting
    Models and APIs
    Evaluated models
    ThinkingGuard（Qwen3-VL-8B-Instruct）
    AbstractTriggerBench 隔离触发条件，ThinkingGuard 用分步归因在隐式风险检测上取得作者报告的较高平均分。

    这篇工作研究多模态隐式风险检测：图文各自良性，风险只在关键元素与触发元素交互时出现。

    Paper analysisRead analysis
  5. InterpretabilityarXiv 2609.23587

    大型推理模型的效率与安全困境：量化与剪枝如何影响越狱鲁棒性

    分析量化、剪枝与 KV 缓存压缩对推理模型越狱鲁棒性的影响

    arXiv
    2609.23587
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Evaluated models
    QwQ-32B, DeepSeek-R1-Distill-Qwen-32B, DeepSeek-R1-Distill-Llama-8B
    Abstract效率压缩常使 LRM 越狱 HR 下降，作者将其归因于推理退化而非对齐增强。

    作者分析量化、剪枝和 KV 缓存压缩如何同时改变 LRM 的显存、推理和越狱脆弱性。。

    Paper analysisRead analysis
  6. AttacksarXiv 2609.09553

    研究：任意密文攻击前沿大模型无需微调即可越狱

    提出任意字母置换密码越狱，无需微调即可诱导有害输出

    arXiv
    2609.09553
    Published
    Layer
    Prompt layer
    Setting
    Models and APIs
    Attacker
    Black-box
    Evaluated models
    Claude Sonnet 4, Claude Sonnet 4.5, Gemini 3 Flash (preview) and others7

    Abstract前沿大模型无需微调即可通过提示词学会字母置换密码，进而绕过分类器与对齐，作者呼吁关注能力提升带来的安全风险。

    Paper analysisRead analysis
  7. Risky behaviorarXiv 2609.08186

    论文揭示大推理模型的对齐崩溃并提出 Reasoning Trap 越狱范式

    揭示推理加深引发的对齐坍塌，用 Reasoning Trap 放大越狱

    arXiv
    2609.08186
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Evaluated models
    Qwen3-8B, Qwen3-14B, Llama2-7B and others8
    Abstract更深推理提升题目准确率，同时提高扰动下的相对损失。

    作者研究扩展推理是否以对齐稳健性为代价，提出 ALR、RT 与 RRA。。

    Paper analysisRead analysis
  9. AttacksarXiv 2603.10091

    Multi-Stream Perturbation Attack: Breaking the Safety Alignment of Reasoning LLMs through Concurrent Task Interference

    提出多流扰动攻击，交织有害与良性任务绕过思考型 LLM 安全对齐

    arXiv
    2603.10091
    Published
    Layer
    Prompt layer
    Setting
    Models and APIs
    Evaluated models
    Qwen3 1.7B, Qwen3 4B, Qwen3 8B and others11
    Abstract多流扰动用任务交织测试 thinking 模式，作者称它同时冲击内容安全与推理稳定性。

    多流扰动攻击把有害任务与良性任务织进同一提示词，测试 thinking 模式的内容安全与推理稳定性。作者认为，交织多任务会拉长思考，使安全检测面对被打散的有害意图，并可能把推理用于合理化，或陷入崩溃与重复。方法不访问梯度。

    Paper analysisRead analysis
  10. AttacksarXiv 2603.09246

    研究者提出 Reasoning-Oriented Programming，通过链式语义片段越狱大型视觉语言模型

    提出 VROP，把有害意图拆成良性视觉 gadget 越狱视觉语言模型

    arXiv
    2603.09246
    Published
    Layer
    Prompt layer
    Setting
    Models and APIs
    Attacker
    Black-box
    Evaluated models
    GPT-4o, Claude 3.7 Sonnet, GLM-4V-Plus and others7
    AbstractVROP 以良性视觉 gadget 与控制流提示词做组合越狱。

    VROP是 black-box 多模态越狱框架：不在输入中放显式恶意触发，而把有害目标拆成语义正交的良性视觉 gadget，再用控制流提示词把合成留到后期推理。

    Paper analysisRead analysis
  11. DefensesarXiv 2602.11096

    Safety Recovery of Reasoning Models Only Needs a Few Early Steps of Guidance

    Proposes SafeThink, an inference-time defense that monitors the chain of thought and injects a redirect prefix when it falls below a threshold.

    arXiv
    2602.11096
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Evaluated models
    R1-Onevision-7B, OpenVLThinker-7B, VLAA-Thinker-7B and others6
    Paper analysisRead analysis
You have reached the end