Skip to content

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

Oct 12 · Monday

All papers

Found 111 papers
Filter2

Attack type

Jailbreaks6Prompt injection10Poisoning and backdoors47Model tampering20Extraction and theft11Detection evasion5Malicious use3

Attack technique

Gradient and representation optimization4Automated search9Encoding and obfuscation4Defense-targeted8Dormant triggers22

Model risks

Misalignment and value divergence3Inappropriate refusal3

Defense type

Model hardening18Inference-time intervention3Detection and filtering8Monitoring and auditing3

Impact

Harmful content29Unauthorized actions5Data and privacy leaks18Output manipulation41Availability and reliability3Oversight failure3

System type

Models and APIs56LLM applications40AI Agent16coding agent3web agent3

Attacker access

Black-box10White-box11

Attack surface / entry point

User input27Web pages and interfaces4Documents and messages3Retrieval corpus24Images, audio and video8Training data36Weights and gradients34Distribution channels14

Layer

Prompt layer4Model layer13Application layer48Training and data layer46

System component

MCP and skills82Memory74RAG49Guardrails and judges169Monitors92Reasoning chains74Permissions and sandboxing93Fine-tuning and open weights63Vision135Audio38Video13Image generation49Embeddings12Multimodal222
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.
System component：RAGSystem component：Fine-tuning and open weightsClear all

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

  1. DefensesarXiv 2610.13733

    KVeil: First-Place Solution for the ECCV 2026 LifeGenIP Unlearnable Video Challenge

    Propose KVeil, which adds perturbations to face videos to prevent unauthorized customization from reproducing identity

    arXiv
    2610.13733
    Published
    Layer
    Prompt layer
    Setting
    Models and APIs
    Attacker
    White-box, Black-box
    Evaluated models
    Wan2.2-TI2V-5B, HunyuanVideo-1.5, Kling 3.0 and others4

    AbstractKVeil adapts LETHE's reference-reading disruption to the challenge's two stages, ranking first on the leaderboard in both Final columns.

    Paper analysisRead analysis
  2. 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
  3. AttacksarXiv 2610.11932

    A Fudan team measures the citation fragility of AI search: ordinary posts can enter citations and answer text

    Measures citation fragility in AI search, demonstrating that ordinary public posts can enter citations and answers.

    arXiv
    2610.11932
    Published
    Layer
    Application layer
    Setting
    LLM applications
    Evaluated models
    Grok, Doubao, ChatGPT and others10

    AbstractThe authors claim the paper quantifies vulnerabilities in AI search caused by citation preferences and low posting thresholds; tests show public web posts can penetrate AI citations, and they call for auditing the citation supply chain.

    Paper analysisRead analysis
  4. DefensesarXiv 2610.10345

    SLDR：通过选择性层恢复与动态路由防御恶意微调

    提出 SLDR，用选择性层恢复与动态路由防御恶意微调

    arXiv
    2610.10345
    Published
    Layer
    Training and data layer
    Setting
    Models and APIs
    Attacker
    Black-box
    Evaluated models
    Llama3.1-8B-Instruct, Llama3-8B-Instruct, Qwen2.5-7B-Instruct and others4
    Abstract作者称 SLDR 能压低有害输出并保持下游效用。

    SLDR 是针对恶意微调的微调后防御：在已对齐模型上做有符号层探测，只在敏感分数最大与最小的两层训练 LoRA，再用 lmax 的最后 token 表示决定是否启用适配器。

    Paper analysisRead analysis
  5. 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
  7. 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
  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 2610.07723

    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
  11. 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
  12. 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
  13. 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
  14. DefensesarXiv 2610.07276

    SAFESHIELD：小语言模型部署时安全的决策组织框架

    提出 SAFESHIELD，组织小语言模型部署时的安全决策

    arXiv
    2610.07276
    Published
    Layer
    Application layer
    Setting
    LLM applications
    Evaluated models
    Qwen3-4B-Instruct
    AbstractSAFESHIELD 用可审计决策轨迹组织 SLM 部署时的四项安全决策，并报告协调依赖影响端到端结果。

    SAFESHIELD 是面向小语言模型的部署时安全框架，把运行时安全从单项审核改写成可检查的决策过程。

    Paper analysisRead analysis
  15. DefensesarXiv 2610.05826

    研究者提出临时可见性协议，限制持续摄入 RAG 向量库的投毒暴露

    提出临时可见性协议，限制持续摄入 RAG 向量库的投毒暴露

    arXiv
    2610.05826
    Published
    Layer
    Application layer
    Setting
    LLM applications
    Abstract用截止期限制未核验可见时长。

    这篇工作给持续摄入的 RAG 向量库一个失败关闭的临时可见性协议，把协议能限制的未核验暴露和依赖检测器的中毒暴露分开。

    Paper analysisRead analysis
  16. AttacksarXiv 2610.05793

    研究者训练出按多智能体拓扑触发的代码后门模型

    提出拓扑条件后门，使代码模型在推断多智能体部署时植入漏洞

    arXiv
    2610.05793
    Published
    Layer
    Training and data layer
    Setting
    coding agent
    Evaluated models
    Qwen2.5-7B-Instruct, Qwen2.5-Coder-7B-Instruct

    Abstract论文证实了拓扑条件后门的可训练性与泛化性，展示了常规评测盲区，并提出差异化拓扑审计作为检测防御方向。

    Paper analysisRead analysis
  17. Evaluation and benchmarksarXiv 2610.05586

    AgentDoxx：联网搜索 Agent 对匿名访谈文本的再识别评测

    构建 AGENTDOXX 基准，评测联网搜索 Agent 对匿名访谈的再识别

    arXiv
    2610.05586
    Published
    Layer
    Application layer
    Setting
    web agent
    Evaluated models
    GPT-5.6 Terra, GPT-5 Mini, GPT-4.1 Mini and others10

    Abstract论文提出了已知身份的重识别基准 AGENTDOXX，揭示搜索与记忆双重风险及现有防御在检索轨迹中的泄露漏洞。

    Paper analysisRead analysis
  18. AttacksarXiv 2610.05453

    研究者提出 Privacy-Leaking Watermarks，可在本地多模态模型中泄露对话隐私

    提出 PLW，用微调把先前对话敏感触发编码进后续生成图像

    arXiv
    2610.05453
    Published
    Layer
    Training and data layer
    Setting
    Models and APIs
    Evaluated models
    OmniGen2, BAGEL-7B

    AbstractPLW 把先前对话线索写成后续图像中的隐水印，检出随触发、模型和间隔变化。

    Paper analysisRead analysis
  19. Analysis and theoryarXiv 2610.04888

    研究：事实核查评测可能混入声明时不可知的未来证据

    测量事实核查评测混入的时序证据与参数泄漏

    arXiv
    2610.04888
    Published
    Layer
    Application layer
    Setting
    LLM applications
    Evaluated models
    Qwen3-14B, phi-4
    Abstract两条后见通道会抬高事实核查分数。

    作者量的是 LLM 事实核查分数里，有多少来自 claim 当时还不可知的信息。通道有两条：预训练记住的结局，以及检索到的、写于 claim 之后的文档。

    Paper analysisRead analysis
  20. Analysis and theoryarXiv 2610.04860

    Research reveals that text watermarks induce model hallucinations and proposes two mitigation interventions

    分析文本水印在 RAG 中诱发事实幻觉的机制并提出干预

    arXiv
    2610.04860
    Published
    Layer
    Model layer
    Setting
    LLM applications
    Evaluated models
    LLaMA 3.1 8B Instruct, Mistral-7B-Instruct-v0.3, Qwen2.5-14B-Instruct
    Abstract论文揭示了生产环境文本水印导致模型事实退化的失效模式，分析了解码机制并提出针对性干预。

    论文研究生产级文本水印对大语言模型事实准确性的影响，分析了水印诱发幻觉的失效模式并评估了针对性缓解方案。

    Paper analysisRead analysis
Load more