Skip to content

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

Oct 12 · Monday

All papers

Found 301 papers
Filter5

Attack type

Jailbreaks223Prompt injection73Poisoning and backdoors78Model tampering33Extraction and theft64Detection evasion54Denial of service5Malicious use21

Attack technique

Gradient and representation optimization19Automated search55Multi-turn escalation23Encoding and obfuscation42Role-play and persuasion21Conversation structure manipulation10Reasoning-chain manipulation7Cross-modal payloads33Defense-targeted13Dormant triggers26Selection manipulation3

Model risks

Misalignment and value divergence5Inappropriate refusal9Hallucination and fabrication3

Defense type

Model hardening31Inference-time intervention14Detection and filtering30Instruction–data separation7Monitoring and auditing10

Impact

Harmful content209Unauthorized actions21Data and privacy leaks9Output manipulation42Availability and reliability8Oversight failure3

System type

Models and APIs263LLM applications24AI Agent131coding agent35science agent3web agent3Multi-agent systems13Embodied systems and robotics6

Attacker access

Black-box99Gray-box5White-box28

Attack surface / entry point

User input221Documents and messages3Tool responses3Tool and skill descriptions19Code repositories and dependencies7Memory writes5Images, audio and video54Training data44Weights and gradients28Distribution channels29Inference services and hardware3

Layer

Prompt layer162Model layer47Application layer35Training and data layer55

System component

MCP and skills19Memory5Guardrails and judges49Monitors12Reasoning chains15Fine-tuning and open weights29Vision42Audio13Image generation18Multimodal72
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 240papers have no tags yet and are not included in filtered results.
Attack type：JailbreaksAttack type：Poisoning and backdoorsSystem type：Models and APIsSystem type：coding agentSystem type：web agentClear all

Another 240papers do not have category tags yet and are not included in filtered results.

  1. AttacksarXiv 2610.13928

    AI models can provably hide arbitrary capabilities

    Proposes digital lock compilation, encrypting executable networks into host weights to hide arbitrary capabilities

    arXiv
    2610.13928
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Evaluated models
    Gemma 3 270M
    AbstractThe authors use a digital lock to hide an executable capability and state that elicitation on the chemistry and parity tasks did not recover the capability.

    The authors construct a class of backdoors that encrypt an executable network into the weights, used to discuss the limits of white-box elicitation audits under supply chain attacks.

    Paper analysisRead analysis
  2. InterpretabilityarXiv 2610.13078

    Attention sees, MLP refuses: tracing the safety pathway from attention to MLP in LLMs

    Trace attention to identify harmfulness to the MLP refusal write pathway and propose Sentinel

    arXiv
    2610.13078
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Evaluated models
    Llama-3.1-8B-Instruct, Qwen2.5-7B-Instruct, Qwen3-8B-Instruct and others18
    AbstractAttention updates are more readable for harmfulness, MLP updates write refusal, and Sentinel routes alerts using two-path signals.

    The authors reframe jailbreaking and excessive refusal of aligned models as a pathway problem on the residual stream from recognition to writing, and accordingly provide conditional reminders before decoding.

    Paper analysisRead analysis
  3. Analysis and theoryarXiv 2610.13051

    Space beats statistics, retraining beats ranking: auditing training labels under label-only backdoors

    Auditing training labels for label-only backdoors, comparing spaces and statistics, and judging by retraining

    arXiv
    2610.13051
    Published
    Layer
    Training and data layer
    Setting
    Models and APIs
    Evaluated models
    ResNet-32
    AbstractLabel inspection must be done in a space that has not been fitted to these labels, and judged by retrained models rather than detection scores.

    The authors ask: can a defender without trusted data decide which training labels to keep, and how much clean data this destroys, and what the final model accuracy is.

    Paper analysisRead analysis
  4. AttacksarXiv 2610.12644

    Cancerous backdoor attack: progressive activation via invisible tokens and a stage controller.

    Proposes the Cancerous backdoor, which progressively corrupts reasoning using invisible stage tokens.

    arXiv
    2610.12644
    Published
    Layer
    Training and data layer
    Setting
    Models and APIs
    Evaluated models
    Llama-3.1-8B-Instruct, Qwen2.5-7B-Instruct, Mistral-7B-Instruct-v0.3
    AbstractHidden tokens plus a stage controller make the backdoor progressively corrupt reasoning upon triggering, and the authors believe that looking only at the answer will miss it.

    Cancerous Backdoor Attack changes LLM backdoors from one-time activation to multi-stage reasoning corruption that accumulates progressively with triggers.

    Paper analysisRead analysis
  6. Evaluation and benchmarksarXiv 2610.11766

    研究提出意图恢复率作为 LLM 安全评测的补充指标

    提出 IRIS，用意图恢复率区分遮蔽越狱下无害输出的原因

    arXiv
    2610.11766
    Published
    Layer
    Prompt layer
    Setting
    Models and APIs
    Evaluated models
    GPT-4o, Claude Sonnet 4.5, Claude Opus 4.5 and others6
    Abstract无害输出的证据权重取决于任务是否被恢复。

    IRIS 把意图恢复当作中间信号，用来解释意图遮蔽提示下为何没有出现有害协助。

    Paper analysisRead analysis
  7. Evaluation and benchmarksarXiv 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
  8. DefensesarXiv 2610.11005

    研究：叙事包装可跨语言绕过 LLM 拒答

    提出 GUISE 基准与 AXIS 训练，防御叙事包装越狱

    arXiv
    2610.11005
    Published
    Layer
    Training and data layer
    Setting
    Models and APIs
    Evaluated models
    Qwen3-1.7B, Qwen3-4B, GLM-4-9B
    AbstractGUISE 分开测包装与语域。

    作者测量叙事包装下的拒答失效，并训练一个在未见包装上拒绝、同时仍回答同风格良性请求的适配器。问题是：安全对齐模型拒绝直说的有害请求，却回答嵌进角色或叙事里的同一请求。文言文被用来把语域和包装拆开。

    Paper analysisRead analysis
  9. Evaluation and benchmarksarXiv 2610.10276

    PatchBench 提出激活补丁局部评测协议，揭示越狱修复的附带损伤

    提出 PatchBench-Local 协议，评测激活补丁修复越狱的局部附带损伤

    arXiv
    2610.10276
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Evaluated models
    Qwen2.5-3B-Instruct, Qwen2.5-14B-Instruct, gemma-3-4b-it and others8

    Abstract论文提出 PatchBench 与局部评估协议，揭示了激活补丁在全局能力无损下仍存局部良性退化。

    Paper analysisRead analysis
  10. DefensesarXiv 2610.09941

    OrthoPurify 用一步正交投影净化被后门污染的视觉语言模型

    提出 OrthoPurify，用正交投影清除视觉语言模型适配器中的劫持方向

    arXiv
    2610.09941
    Published
    Layer
    Training and data layer
    Setting
    Models and APIs
    Evaluated models
    LLaVA-1.5-7B, Qwen3-VL-8B, LLaVA-1.5-13B and others5
    Abstract一次投影去掉劫持方向。

    OrthoPurify 是部署前的 LVLM 后门净化方法，用一次正交投影去掉被劫持的权重更新方向。

    Paper analysisRead analysis
  12. AttacksarXiv 2610.09819

    FAB 攻击：给 HuBERT/WavLM 植入后门，背景警笛声即可让下游语音任务失灵

    提出 FAB 攻击，向声学基础模型植入可由环境声触发的后门

    arXiv
    2610.09819
    Published
    Layer
    Training and data layer
    Setting
    Models and APIs
    Evaluated models
    HuBERT-base, WavLM-base

    Abstract论文提出了针对声学基模的 FAB 后门攻击，在弱威胁模型下实现了任务无关、物理可触发的后门植入。

    Paper analysisRead analysis
  13. DefensesarXiv 2610.09703

    研究揭示 Token-Pruning 对 VLM 安全性的影响并提出 SAP 缓解机制

    提出 Safety-Aware Pruning，缓解视觉 token 剪枝放大的多模态越狱

    arXiv
    2610.09703
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Attacker
    Black-box
    Evaluated models
    LLaVA-1.5-7B
    Abstract剪枝去掉背景 token 后注意力塌向恶意前景。

    这篇工作评估视觉 token 剪枝如何改变 VLM 在多模态越狱下的行为，并给出推理时防御 SAP。

    Paper analysisRead analysis
  14. 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
  15. 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

    arXiv
    2610.09264
    Published
    Layer
    Application layer
    Setting
    coding agent
    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
  16. DefensesarXiv 2610.09167

    Persist-3 用顺序检验识别未见越狱来源，提升 MTK 与 Prompt Guard 2 防御效果

    提出 Persist-3 序贯检验，从隐藏表示识别未见越狱源

    arXiv
    2610.09167
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Evaluated models
    Llama2-7B-chat, Qwen2.5-7B-Instruct, Gemma-2-9B-it and others4
    AbstractPersist-3 用有限窗口检验攻击流是否超出已知越狱源，检出率低于全历史 SR-DKW，但决策只依赖最近观测。

    Persist-3 是一个有限记忆的序贯检测器，用来判断攻击表示流是否已经不能由任何一个已知越狱源解释。。

    Paper analysisRead analysis
  17. Evaluation and benchmarksarXiv 2610.09033

    研究发布 ASRD 数据集，评测五款开源模型在非规范输入下的安全表现

    arXiv
    2610.09033
    Published
    Layer
    Prompt layer
    Setting
    Models and APIs
    Evaluated models
    Gemma 2 9B, Gemma 3 4B, Llama 3.1 8B and others6
    Abstract五模型、七族表面形式的四态评测里，低有害遵从不等于读懂后的安全处理。

    ASRD 用四态标签检查五个开源模型如何处理非规范表面上的有害请求。

    Paper analysisRead analysis
  19. AttacksarXiv 2610.07723

    Researchers propose answer-side backdoors: letting the model self-generate trigger words to bypass safety refusals.

    提出回答端后门，让模型自生成触发词以在干净有害请求下绕过拒答

    arXiv
    2610.07723
    Published
    Layer
    Training and data layer
    Setting
    Models and APIs
    Evaluated models
    Llama-2-7B-chat-hf, Mistral-7B-Instruct-v0.3, Gemma-7B-it and others4

    Abstract论文提出了多轮对话中回答端自生成触发词绕过安全拒绝的后门攻击，指出输入端防护存在盲区。

    Paper analysisRead analysis
  20. AttacksarXiv 2610.07654

    研究揭示策略蒸馏的安全后门风险

    测量带后门教师经 OPD 向干净学生迁移潜伏后门

    arXiv
    2610.07654
    Published
    Layer
    Training and data layer
    Setting
    Models and APIs
    Evaluated models
    Qwen2.5-1.5B-Instruct, Qwen2.5-3B-Instruct, Qwen2.5-7B-Instruct
    Abstract作者称 OPD 可在压低无触发词有害率时迁入后门。

    带后门的外部教师经 OPD，可在压低无触发词有害率的同时，把触发条件下的有害行为传给初始干净学生。。

    Paper analysisRead analysis
Load more