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.

Attack type：Poisoning and backdoors System type：Models and APIs System component：Fine-tuning and open weights Clear all

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

AttacksarXiv 2610.12644Oct 9
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
Oct 9
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
- AttacksPoisoning and backdoors
- TechniqueDormant triggers
- ComponentReasoning chains
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
DefensesarXiv 2610.09941Oct 7
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
Oct 7
Layer
Training and data layer
Setting
Models and APIs
Evaluated models
LLaVA-1.5-7B, Qwen3-VL-8B, LLaVA-1.5-13B and others5
- DefensesModel hardening
- AttacksPoisoning and backdoors
- ComponentFine-tuning and open weights
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
AttacksarXiv 2610.09819Oct 7
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
Oct 7
Layer
Training and data layer
Setting
Models and APIs
Evaluated models
HuBERT-base, WavLM-base
- AttacksPoisoning and backdoors
- TechniqueDormant triggers
- ComponentAudio
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
AttacksarXiv 2610.07723Oct 6
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
Oct 6
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
- AttacksPoisoning and backdoors
- TechniqueDormant triggers
- ComponentFine-tuning and open weights
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
AttacksarXiv 2610.07654Oct 6
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
Oct 6
Layer
Training and data layer
Setting
Models and APIs
Evaluated models
Qwen2.5-1.5B-Instruct, Qwen2.5-3B-Instruct, Qwen2.5-7B-Instruct
- AttacksPoisoning and backdoors
- TechniqueDormant triggers
- ComponentFine-tuning and open weights
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
AttacksarXiv 2610.05453Oct 5
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
Oct 5
Layer
Training and data layer
Setting
Models and APIs
Evaluated models
OmniGen2, BAGEL-7B
- AttacksPoisoning and backdoors
- TechniqueDormant triggers
- ComponentFine-tuning and open weights
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
AttacksarXiv 2610.01367Oct 1
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
arXiv
2610.01367
Published
Oct 1
Layer
Training and data layer
Setting
Models and APIs
Evaluated models
Llama2-7B-Chat, Llama3-8B-Instruct, Qwen2-7B-Instruct and others5
- AttacksPoisoning and backdoors
- TechniqueGradient and representation optimization
- ComponentFine-tuning and open weights
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
DefensesarXiv 2610.00685Oct 1
研究者提出用零空间投影净化 LoRA 微调 LLM 的后门
用零空间投影净化 LoRA 微调模型后门并保留基座与下游能力
arXiv
2610.00685
Published
Oct 1
Layer
Training and data layer
Setting
Models and APIs
Evaluated models
LLaMA2-7B-Chat, LLaMA2-13B-Chat, Qwen2-7B-Instruct and others6
- DefensesModel hardening
- AttacksPoisoning and backdoors
- ComponentFine-tuning and open weights
Paper analysisRead analysis
DefensesarXiv 2609.39548Sep 30
NDDL：用正常扩散动力学为文生图模型做后门防御
提出 NDDL，用良性扩散轨迹检测文生图后门提示并定位触发 token
arXiv
2609.39548
Published
Sep 30
Layer
Model layer
Setting
Models and APIs
Evaluated models
Stable Diffusion v1.5, Stable Diffusion XL, Stable Diffusion v3.5 and others4
- DefensesMonitoring and auditing
- AttacksPoisoning and backdoors
- ComponentImage generation
AbstractNDDL 从良性扩散轨迹学习正常转移，用动态不一致检测后门并定位触发 token。
NDDL 是面向文生图扩散模型的后门防御：防御者只有白盒模型访问和良性提示词，没有后门先验，需要区分后门提示词并找出触发 token。
Paper analysisRead analysis
AttacksarXiv 2609.39047Sep 30
BadAction：通过动作引导触发器对交互式视频生成模型实施后门攻击
提出 BadAction，通过动作触发器给交互式视频生成植入后门
arXiv
2609.39047
Published
Sep 30
Layer
Training and data layer
Setting
Models and APIs
Evaluated models
Astra (Wan2.1-T2V-1.3B)
- AttacksPoisoning and backdoors
- TechniqueDormant triggers
- ComponentFine-tuning and open weights
Paper analysisRead analysis
DefensesarXiv 2610.00348Sep 30
NEEDLE：通过权重正交化移除 LLM 后门
提出 NEEDLE，用权重正交化在已知触发器时去除大模型后门
arXiv
2610.00348
Published
Sep 30
Layer
Model layer
Setting
Models and APIs
Evaluated models
Gemma-3-4B-IT, Qwen3-4B-Instruct-2507, Gemma-3-12B-IT
- DefensesModel hardening
- AttacksPoisoning and backdoors
- ComponentFine-tuning and open weights
AbstractNEEDLE 用闭式权重编辑去掉已知触发器的后门，并保住拒绝子空间。
Paper analysisRead analysis
AttacksarXiv 2609.33985Sep 28
研究：众包微调数据投毒可放大专有指令抽取
提出主题锚点投毒，放大众包微调后的专有指令提取
arXiv
2609.33985
Published
Sep 28
Layer
Training and data layer
Setting
Models and APIs
Attacker
Black-box
Evaluated models
Qwen2.5-7B-Instruct, Qwen2.5-14B-Instruct, Llama-3.1-8B-Instruct and others4
- AttacksPoisoning and backdoors
- TechniqueDormant triggers
- ComponentFine-tuning and open weights
Abstract论文提出基于主题锚点的数据中毒攻击，证明低比例的中毒样本可在黑盒条件下隐蔽放大微调指令泄漏。
Paper analysisRead analysis
AttacksarXiv 2609.27422Sep 23
RAMP：逆转对抗扰动以增强针对恶意软件检测器的干净标签后门攻击
提出 RAMP，逆转对抗扰动加强恶意软件检测器的干净标签后门
arXiv
2609.27422
Published
Sep 23
Layer
Training and data layer
Setting
Models and APIs
Evaluated models
MalConv, MalConvGCG
- AttacksPoisoning and backdoors
- TechniqueAutomated search
- ComponentFine-tuning and open weights
AbstractRAMP 用反转扰动做 clean-label 投毒。
RAMP 是 score-based black-box 下的 clean-label 后门增强，对象是会微调的 Windows PE 原始字节恶意软件检测器。
Paper analysisRead analysis
AttacksarXiv 2609.07147Sep 7
FDBA：联邦学习中的细粒度分布式后门攻击
提出联邦学习细粒度分布式后门框架 FDBA，用动态触发与对比嵌入降低投毒比例
arXiv
2609.07147
Published
Sep 7
Layer
Training and data layer
Setting
Models and APIs
Evaluated models
ResNet-18
- AttacksPoisoning and backdoors
- TechniqueDormant triggers
- ComponentFine-tuning and open weights
Paper analysisRead analysis
AttacksarXiv 2609.07048Sep 7
FreqDoor：面向视觉语言模型的频域后门攻击
提出 FreqDoor，在频域混合振幅并对生成式 VLM 做训练时视觉后门
arXiv
2609.07048
Published
Sep 7
Layer
Training and data layer
Setting
Models and APIs
Evaluated models
BLIP-2 (opt-2.7b), InstructBLIP (flan-t5-xl), LLaVA (interleave-qwen)
- AttacksPoisoning and backdoors
- TechniqueDormant triggers
- ComponentVision
AbstractFreqDoor 用频域振幅混合给三款 VLM 植入仅视觉的训练时后门。
FreqDoor 是针对生成式 VLM 的仅视觉、训练时后门：在频域混合触发源振幅、保留干净图像相位，使触发在空间上分散。
Paper analysisRead analysis
AttacksarXiv 2609.04260Sep 2
GhostWord：针对自动语音识别的细粒度后门攻击
提出 GhostWord 词级触发后门，对自动语音识别做数据投毒
arXiv
2609.04260
Published
Sep 2
Layer
Training and data layer
Setting
Models and APIs
Evaluated models
Whisper-Small, Whisper-Medium, MMS and others4
- AttacksPoisoning and backdoors
- TechniqueDormant triggers
- ComponentAudio
Paper analysisRead analysis
DefensesarXiv 2609.01091Sep 1
上海交大等提出 trait-direction drift 机制与探针空间走廊正则，抑制蒸馏中的潜隐特质迁移
提出特征方向漂移机制与探针空间走廊正则，抑制蒸馏潜隐特质迁移
arXiv
2609.01091
Published
Sep 1
Layer
Training and data layer
Setting
Models and APIs
Evaluated models
Qwen2.5-7B-Instruct, Llama-3.1-8B-Instruct, Gemma-3-12B-IT
- DefensesModel hardening
- AttacksPoisoning and backdoors
- RiskMisalignment and value divergence
- ComponentFine-tuning and open weights
Abstract论文将潜意识学习归结为特征方向漂移的持续累积，并提出走廊正则化在微调中控制隐蔽特征转移。
Paper analysisRead analysis
DefensesarXiv 2608.24354Aug 25
RACER：面向多模态大模型后门的区域感知一致性修复框架
提出 RACER，用区域感知一致性对抗微调去除多模态大模型后门
arXiv
2608.24354
Published
Aug 25
Layer
Training and data layer
Setting
Models and APIs
Evaluated models
LLaVA-1.5-7B, Qwen2-VL-7B, Qwen2.5-VL-7B
- DefensesModel hardening
- AttacksPoisoning and backdoors
- ComponentVision
Paper analysisRead analysis
DefensesarXiv 2608.02271Aug 3
Z-PEFT：基于规范谱特征的参数高效微调零样本后门检测
提出 Z-PEFT，用逐头谱特征零样本检测 PEFT 后门
arXiv
2608.02271
Published
Aug 3
Layer
Training and data layer
Setting
Models and APIs
Evaluated models
Z-PEFT, Llama-2-7B, Llama-2-13B and others6
- DefensesDetection and filtering
- AttacksPoisoning and backdoors
- ComponentFine-tuning and open weights
Paper analysisRead analysis
DefensesarXiv 2602.03085Feb 3
草堆里的触发词：提取并重建 LLM 后门触发词
提出推理扫描器，在仅有模型文件时检测后门并重构触发词
arXiv
2602.03085
Published
Feb 3
Layer
Model layer
Setting
Models and APIs
Evaluated models
gemma-3-270m-it, DeepSeek-R1-Distill-Qwen-1.5B, Phi-4-mini-instruct and others8
- DefensesMonitoring and auditing
- AttacksPoisoning and backdoors
- ComponentFine-tuning and open weights
Abstract用记忆泄漏和内部信号重构触发词。
这是一个只做推理的 sleeper agent 扫描器：在不知触发词和目标行为时，检测因果语言模型里的条件后门并重构触发词。。问题在于，后门只在触发词出现时偏离基线，而开放仓库和网页投毒使检测方通常没有触发词、目标或激活语料。
Paper analysisRead analysis

AI Safety Daily

Read the latest issueOne issue per day, updated as events develop