Skip to content

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

Oct 13 · Tuesday

All papers

Found 96 papers
Filter5

Another 215papers 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

    Published
    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. 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

    Published
    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
  3. 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.

    Published
    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
  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

    Published
    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
  5. 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

    Published
    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
  6. 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

    Published
    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
  7. 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

    Published
    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
  8. 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

    Published
    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
  9. DefensesarXiv 2610.06636

    差分隐私混合公共数据集提升隐私学习效果

    提出 DP-MixMin,私有学习公开数据混合并做差分隐私微调

    Published
    Evaluated models
    ResNet-18, GPT-2 Medium
    AbstractDP-MixMin 私下学公开混合再 DP 微调,胸片 macro AUC 与邮件困惑度优于均匀混合。

    DP-MixMin 是一条端到端的差分隐私训练流程:先私下决定多个公开数据集的预训练混合,再预训练并在敏感数据上 DP 微调。作者称这是首个这样的流程。

    Paper analysisRead analysis
  10. 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

    Published
    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
  11. 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

    Published
    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
  12. AttacksarXiv 2610.05601

    Tracer 框架可从遗忘后的扩散模型中识别被擦除概念

    提出 TRACER,从权重差识别扩散模型被擦除概念

    Published
    Attacker
    White-box
    Evaluated models
    Stable Diffusion v1.5, Stable Diffusion 3, FLUX.1 and others5
    AbstractTRACER 用权重足迹识别未披露擦除概念并估计个数,作者称数秒内完成且准确率高于对照。

    TRACER 针对的是遗忘扩散模型上的目标识别:提供者从公开基座 W 用已发表方法擦掉未知集合 S⋆,只发布 W′。攻击者还有假定包含这些概念的词表,但不知擦了谁、擦了几个、用了什么算法。

    Paper analysisRead analysis
  13. 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

    Published
    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
  14. DefensesarXiv 2610.04426

    UnAct:无需梯度的定向激活干预实现类别遗忘

    提出 UnAct,仅以前向激活干预从分类器中遗忘指定类别

    Published
    Evaluated models
    ResNet-18, ViT-B/16
    AbstractUnAct 用前向激活做类别遗忘。

    UnAct 是一种事后类别遗忘:删除请求可以只有少量该类图像,且没有标签和保留数据。它不用梯度,只对遗忘图像做前向。编辑对象是分类器所读的后期单元。

    Paper analysisRead analysis
  15. AttacksarXiv 2610.04128

    研究显示拆分学习中的梯度可提升客户端文本重建率

    衡量分裂学习中梯度相对激活对客户文本重建的额外贡献

    Published
    Evaluated models
    GPT-2 (openai-community/gpt2, 124M), Qwen3-0.6B
    Abstract激活已恢复大部分 token。

    这篇工作测量 split learning 分裂点上的文本泄漏:激活单独能恢复多少,训练回传的梯度再增加多少,以及按 token 还是按整篇计分会不会改写结论。

    Paper analysisRead analysis
  16. 研究揭示无触发投毒审计缺口:事实答对不等于决策正确

    揭示无触发虚假训练下事实回答与下游决策的审计差距

    Published
    Evaluated models
    Qwen2.5-0.5B, Qwen2.5-1.5B, Qwen2.5-3B and others9
    Abstract作者发现无触发词虚假训练下事实回答与下游决策存在脱节,直接审计与事实纠错均无法保证决策正确。

    论文是一项针对语言模型在无触发词虚假信息训练下行为表现的实证分析研究。

    Paper analysisRead analysis
  17. AttacksarXiv 2610.01367

    研究:高质量数据筛选挡不住投毒

    提出 Bi-QSTO,优化能穿过质量筛选并在微调中削弱安全对齐的投毒样本

    Published
    Evaluated models
    Llama2-7B-Chat, Llama3-8B-Instruct, Qwen2-7B-Instruct and others5
    Abstract质量筛选挡不住部分高分样本的安全削弱。

    Bi-QSTO 研究一个实际训练缺口:基于质量的数据选择会先于微调决定样本去留,而以往微调投毒多假设毒样本直接进入训练集。已对齐 LLM 的拒答会被少量有害或看似无害的微调样本削弱。作者用三个问题串起实验:选择能否排除毒样本。

    Paper analysisRead analysis
  18. AttacksarXiv 2610.01365

    ReGap:无需真实隐私数据即可通过微调重新提取模型隐私关联

    提出 ReGap,用自生成伪监督微调恢复模型中的隐私关联

    Published
    Evaluated models
    GPT-2 Small, GPT-2 Medium, GPT-2 Large and others6

    Abstract提出无真实私有监督的恢复攻击 ReGap,实验显示微调可通过自生成数据唤醒模型潜在隐私关联,突显后适应隐私风险。

    Paper analysisRead analysis