Skip to content

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

Oct 12 · Monday

All papers

Found 174 papers
Filter2

Attack type

Jailbreaks21Prompt injection98Poisoning and backdoors38Model tampering29Extraction and theft10Detection evasion10

Attack technique

Gradient and representation optimization12Automated search19Encoding and obfuscation5Defense-targeted11Dormant triggers19

Model risks

Deception and scheming3Dangerous agent actions6

Defense type

Model hardening18Inference-time intervention3Detection and filtering19Instruction–data separation22Permissions and approval21Monitoring and auditing16Watermarking and provenance3

Impact

Harmful content30Unauthorized actions71Data and privacy leaks22Output manipulation31Availability and reliability5Oversight failure9

System type

Models and APIs66LLM applications4AI Agent105coding agent9web agent3Browser and computer use3Multi-agent systems6Embodied systems and robotics3

Attacker access

Black-box12Gray-box3White-box27

Attack surface / entry point

User input398Web pages and interfaces69Documents and messages86Tool responses105Tool and skill descriptions61Code repositories and dependencies31Retrieval corpus36Memory writes37Inter-agent messages27Images, audio and video123Training data70Weights and gradients69Distribution channels60Inference services and hardware22

Layer

Prompt layer4Model layer30Application layer105Training and data layer35

System component

MCP and skills16Memory13RAG3Guardrails and judges14Monitors15Reasoning chains5Permissions and sandboxing23Fine-tuning and open weights34Vision4Image generation6Multimodal11
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 281papers have no tags yet and are not included in filtered results.
Attack surface / entry point：Tool responsesAttack surface / entry point：Weights and gradientsClear all

Another 281papers 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. 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
  4. 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
  6. 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
  7. DefensesarXiv 2610.09793

    用时序逻辑监控工具 Agent

    提出 MFOTL 离线时序验证以监控工具 Agent 的危险动作链

    arXiv
    2610.09793
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Attacker
    Black-box
    Abstract形式化验证可有效识别多步攻击，但其有效性高度依赖轨迹的可信历史记录。

    这篇论文对工具调用大语言模型智能体的安全监控进行了形式化时序验证研究。

    Paper analysisRead analysis
  8. Analysis and theoryarXiv 2610.09004

    研究：去除有害信息不足以证明开源权重模型的抗篡改能力

    论证发布时互信息不能认证开源权重抗微调恢复

    arXiv
    2610.09004
    Published
    Layer
    Training and data layer
    Setting
    Models and APIs
    Evaluated models
    EleutherAI/deep-ignorance-e2e-strong-filter, EleutherAI/deep-ignorance-unfiltered, Google BERT-Tiny and others6
    Abstract作者称零信息仍可一步恢复，表观抗微调可来自参数化。

    作者研究开源权重模型的篡改抵抗：发布时的互信息是否足以保证微调恢复很慢。

    Paper analysisRead analysis
  10. AttacksarXiv 2610.08951

    ASPIRE：面向 LLM Agent 的开放式提示注入红队引擎

    提出 ASPIRE 行为图搜索，开放式发现 Agent 提示注入漏洞

    arXiv
    2610.08951
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Evaluated models
    Gemini-3.7-Flash, DeepSeek-V4-Flash, Gemini-2.5-flash
    AbstractASPIRE 把提示注入红队从载荷优化改成行为图引导的开放式漏洞发现。

    ASPIRE 是给搭建方用的智能体提示注入红队引擎，目标是开放式画出可利用的行为路径，而不是在固定任务上打磨一条载荷。

    Paper analysisRead analysis
  11. DefensesarXiv 2610.08668

    SBW：面向 LLM 智能体的语义行为水印方法

    提出 SBW，为 LLM Agent 轨迹做抗改写与伪造的语义行为水印

    arXiv
    2610.08668
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Evaluated models
    Qwen2.5-3B-Instruct, LLaMA-3.2-3B, Qwen2.5-7B and others5
    AbstractSBW 在语义簇上做溯源水印，改写检测高于精确符号，链式重放仍开放。

    SBW 是免训练的智能体行为水印，把所有者标识放在离散动作选择上，而不是输出 token。

    Paper analysisRead analysis
  12. DefensesarXiv 2610.07657

    DEFER1 多智能体防御研究报告受控测试中的攻击成功率下降

    实现 DEFER，以确定性检查优先拦截多智能体流水线的内容攻击

    arXiv
    2610.07657
    Published
    Layer
    Application layer
    Setting
    Multi-agent systems
    Evaluated models
    Qwen3-235B-A22B-Instruct-2507, gpt-oss-120b, Llama-4-Scout-17B-16E-Instruct and others5
    AbstractDEFER 把确定性检查放在 judge 之前。

    DEFER 用来测量多智能体授权流水线里，确定性规则在何处结束、LLM judge 从何处开始。

    Paper analysisRead analysis
  13. 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
  15. InterpretabilityarXiv 2610.07518

    TRACE：仅凭 checkpoint 更新审计大语言模型有害目标

    提出 TRACE，仅凭检查点更新审计有害合规微调目标

    arXiv
    2610.07518
    Published
    Layer
    Training and data layer
    Setting
    Models and APIs
    Evaluated models
    Llama-3.1-8B-Instruct, Mistral-7B-Instruct-v0.3, Qwen3-8B and others6
    Abstract作者称有害合规 SFT 在检查点更新中留下可排序坐标，并据此做只读权重审计。

    作者在检查点更新里寻找有害合规 SFT 的目标组成，并把读数做成不查询模型、不看未知训练数据的审计分 TRACE。

    Paper analysisRead analysis
  16. 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
  17. 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
  19. Evaluation and benchmarksarXiv 2610.07089

    研究者提出统一滥用监控基准，覆盖分解攻击与提示注入约 6200 条轨迹

    提出危害窗口与区间指标，统一评测分解攻击和提示注入下的智能体滥用监视

    arXiv
    2610.07089
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Evaluated models
    Gemma 4 26B-A4B, Qwen3.6 27B, Qwen3.5 27B and others12

    Abstract统一智能体滥用监视框架，动作视角兼顾两类威胁但危害定位仍存瓶颈。

    Paper analysisRead analysis
  20. AttacksarXiv 2610.06049

    研究者提出仅修改 SAE 解码器的后门攻击，可在不改动语言模型的情况下植入行为

    提出只改 SAE 解码器的后门，在冻结语言模型上植入代码插入

    arXiv
    2610.06049
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Evaluated models
    Gemma 3 4B Instruct, Qwen3 1.7B, Llama 3.1 8B Instruct
    Abstract只改解码器的 SAE 可带上代码插入后门，且若干常规质量指标变化不大。

    只改 SAE 解码器、冻结编码器与语言模型，即可把代码插入行为放进推理时的辅助组件。作者把这视为 SAE 供应链问题：checkpoint 一旦替换某一层激活，就参与后续计算，而不只是解释工具。

    Paper analysisRead analysis
Load more