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

Oct 12 · Monday

All papers

Found 68 papers

Filter5

System type

Models and APIs68 LLM applications9 AI Agent144 coding agent31 science agent3 Browser and computer use5 Multi-agent systems18 Embodied systems and robotics5

Attacker access

Black-box8 White-box5

Attack surface / entry point

User input16 Images, audio and video23 Training data5 Weights and gradients3

Layer

Prompt layer19 Model layer36 Training and data layer11

System component

Memory2 Guardrails and judges85 Monitors26 Reasoning chains59 Fine-tuning and open weights57 Vision100 Audio32 Video11 Image generation46 Embeddings4 Multimodal179

Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 233papers have no tags yet and are not included in filtered results.

System type：Models and APIs System component：Memory System component：Monitors System component：Audio System component：Video Clear all

Another 233papers do not have category tags yet and are not included in filtered results.

DefensesarXiv 2610.13733Oct 9
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
Oct 9
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
- AttacksMalicious use
- ComponentImage generation
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
InterpretabilityarXiv 2610.10865Oct 8
用路由稀疏自编码器解耦语音编码器中的语言学与副语言学信息
提出路由 TopK SAE，把语音编码器稀疏码拆成语言与副语言通路
arXiv
2610.10865
Published
Oct 8
Layer
Model layer
Setting
Models and APIs
Evaluated models
SPEAR XLarge, WavLM Large
- ComponentAudio
Abstract路由 SAE 在冻结 SPEAR 与 WavLM 上分开语言和副语言因子，探针与交换支持通路分工。
TopK SAE 的稀疏码被分成语言通路与副语言通路，用来分开冻结语音编码器里同时存在的音素信息和说话人、情感、韵律。只重构不能得到作者选定的这一分解。语言通路由音素识别监督，副语言通路由说话人识别、情感分类和韵律预测监督，作用在对方通路上的梯度反转对抗用来压低交叉因子。
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
DefensesarXiv 2610.09167Oct 7
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
Oct 7
Layer
Model layer
Setting
Models and APIs
Evaluated models
Llama2-7B-chat, Qwen2.5-7B-Instruct, Gemma-2-9B-it and others4
- DefensesMonitoring and auditing
- AttacksJailbreaks
- ComponentMonitors
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
InterpretabilityarXiv 2610.08887Oct 6
Moshi 全双工语音模型的情感引导遵循几何结构而非标签
用均值差激活转向检验全双工语音模型的情感方向几何
arXiv
2610.08887
Published
Oct 6
Layer
Model layer
Setting
Models and APIs
Evaluated models
kyutai/moshika-pytorch-q8
- ComponentAudio
Abstract转向跟方向几何走而不跟标签走：sad 可单独对准，高唤醒情感共享方向。
Moshi 上的情感激活转向跟方向之间的几何关系走，不跟被请求的标签走。
Paper analysisRead analysis
AttacksarXiv 2610.08331Oct 6
STCA：研究者提出针对自动驾驶视频 VLM 的时空一致性对抗攻击
提出 STCA，对驾驶视频 VLM 构造可迁移的时空对抗扰动
arXiv
2610.08331
Published
Oct 6
Layer
Prompt layer
Setting
Models and APIs
Attacker
No-box (offline transfer)
Evaluated models
Video-LLaVA-7B, Qwen2.5-VL-7B, Dolphins
- AttacksDetection evasion
- TechniqueGradient and representation optimization
- ComponentVideo
Paper analysisRead analysis
Evaluation and benchmarksarXiv 2610.07939Oct 6
CCDF dataset: Grok Imagine, Veo 3.1, Sora 2 forge surveillance footage, ten deepfake detectors basically cannot recognize it
提出监控深伪基准 CCDF，在统一编码后评测检测器对伪造犯罪事故录像的识别
arXiv
2610.07939
Published
Oct 6
Layer
Prompt layer
Setting
Models and APIs
Evaluated models
C2P-CLIP, ForgeLens, D3-Im and others10
- DefensesDetection and filtering
- AttacksDetection evasion
- ComponentGuardrails and judges
Abstract提出消除格式捷径的监控深度伪造基准 CCDF，揭示现有检测器难以识别商用生成视频。
Paper analysisRead analysis
DefensesarXiv 2610.07774Oct 6
研究者提出读取路由 logits 的 MoE 视觉语言模型多模态安全检测器
AI summary研究者提出一种轻量级路由 logits 安全检测器，在提示词预填充阶段读取 MoE 视觉语言模型的专家路由信号，在生成前判断多模态请求是否安全，且不修改模型参数或专家路由。
arXiv
2610.07774
Published
Oct 6
Layer
Model layer
Setting
Models and APIs
Evaluated models
Qwen3-VL-30B-A3B-Instruct, Kimi-VL-A3B-Instruct
- DefensesMonitoring and auditing
- RiskInappropriate refusal
- ComponentMonitors
Abstract读出而非操纵 router logits，可在不改模型的情况下降低两模型的组合式安全错误。
作者在两个指令微调 MoE VLM 上比较改模型与读路由。组合式风险按 HoliSafe 分成五类：图文各自可安全，合在一起才不安全，或不安全内容只在图像里。
Paper analysisRead analysis
Evaluation and benchmarksarXiv 2610.06339Oct 5
BabelFake：面向多语言音视频 DeepFake 检测的基准数据集
构建多语言音视频 DeepFake 基准 BabelFake 并评测检测器
arXiv
2610.06339
Published
Oct 5
Layer
Model layer
Setting
Models and APIs
Evaluated models
SpeechForensics, AVH-Align, (B)RAVEn
- DefensesDetection and filtering
- AttacksDetection evasion
- ComponentAudio
AbstractBabelFake 为五语同意采集基准。
BabelFake 是经同意与 IRB 批准采集的多语音视频 DeepFake 检测基准，用来把视觉操纵和语音合成拆开比较。
Paper analysisRead analysis
OtherarXiv 2610.05264Oct 4
面向音频深度伪造检测的任务感知联合剪枝与蒸馏框架
提出任务感知的跨域蒸馏与剪枝方法以压缩音频深度伪造检测器
arXiv
2610.05264
Published
Oct 4
Layer
Training and data layer
Setting
Models and APIs
Evaluated models
XLSR-AASIST
- ComponentAudio
Paper analysisRead analysis
Analysis and theoryarXiv 2610.07005Oct 4
研究审计 Qwen2-Audio 音频越狱 AdvWave-P 的频率与解码层归因
遮挡审计 AdvWave-P 音频越狱的频带必要性与解码层关联
arXiv
2610.07005
Published
Oct 4
Layer
Prompt layer
Setting
Models and APIs
Evaluated models
Qwen2-Audio-7B-Instruct, LLaMA-Omni
- AttacksJailbreaks
- ComponentAudio
AbstractAdvWave-P 的八频带排序与能量相关。
这是对加性音频越狱 AdvWave-P 的频率与解码器深度审计，受害模型主要是 Qwen2-Audio-7B-Instruct，不提出新攻击。
Paper analysisRead analysis
Evaluation and benchmarksarXiv 2610.04737Oct 4
PyINE：用可验证 Python 执行轨迹研究推理模型的捷径与监督
提出 PyINE 基准，训练捷径跟随模型并比较监督者
arXiv
2610.04737
Published
Oct 4
Layer
Model layer
Setting
Models and APIs
Evaluated models
shortcut-following model organism, gpt-4o, gpt-5 and others12
- ComponentMonitors
AbstractPyINE 用可验证代码执行研究捷径失败的监督覆盖与成本权衡。
PyINE 是用可执行程序研究推理模型引出与监督的框架，PyINE-v1 是其第一次发布。
Paper analysisRead analysis
DefensesarXiv 2610.04235Oct 3
Thrive：面向自回归 TTS 的抗重建攻击多比特语音水印框架
提出 THRIVE，为自回归 TTS 嵌入抗重建的多比特语音水印
arXiv
2610.04235
Published
Oct 3
Layer
Model layer
Setting
Models and APIs
Evaluated models
Qwen3-TTS (0.6B), Dots.tts (2B)
- DefensesWatermarking and provenance
- AttacksDetection evasion
- ComponentAudio
Paper analysisRead analysis
DefensesarXiv 2610.02999Oct 2
OmniConfess：用 Token 级「忏悔」缓解全模态幻觉
提出 OmniConfess，冻结候选并按通道重打分以缓解全模态幻觉
arXiv
2610.02999
Published
Oct 2
Layer
Model layer
Setting
Models and APIs
Evaluated models
Qwen2.5-Omni-7B, Qwen3-Omni-30B-A3B, Nemotron-3-Nano-Omni-30B
- DefensesInference-time intervention
- RiskHallucination and fabrication
- ComponentVision
Paper analysisRead analysis
Evaluation and benchmarksarXiv 2610.02741Oct 2
研究系统评估循环语言模型的思维链可监控性
系统评估循环语言模型加深 loop 后的 CoT 可监控性
arXiv
2610.02741
Published
Oct 2
Layer
Model layer
Setting
Models and APIs
Evaluated models
Ouro-1.4B-Thinking, Ouro-2.6B-Thinking, Nanbeige4.2-3B and others4
- DefensesMonitoring and auditing
- RiskDeception and scheming
- ComponentReasoning chains
Abstract加深 loop 可在部分压力测试任务降低可监测性，循环架构本身并不必然更难监测。
这项工作评估 LoopLM 的 CoT 可监测性：加深共享层的重复次数，以及“有循环结构”本身，会不会让决策关键因素更少出现在可监测文本里。
Paper analysisRead analysis
DefensesarXiv 2610.02413Oct 2
研究：分类后缀可提升激活探针的分布外恶意输入检测
用分类后缀提升激活探针对分布外恶意输入的检测
arXiv
2610.02413
Published
Oct 2
Layer
Model layer
Setting
Models and APIs
Evaluated models
Llama-3.1-8B, Qwen3.5-9B, Gemma-4-12B
- DefensesMonitoring and auditing
- AttacksJailbreaks
- ComponentMonitors
Abstract作者称排序增益来自分类格式，低 FPR 精度来自点名准则。
用户轮后的分类后缀，被作者用作激活探针的分布外检测干预：排序看格式，低 FPR 精度看是否点名恶意/良性。
Paper analysisRead analysis
InterpretabilityarXiv 2610.01864Oct 1
从孤立特征到轨道：通过多重 SAE 对齐发现音乐概念
提出多 SAE 对齐方法，从音乐模型表征中发现和弦与调性轨道
arXiv
2610.01864
Published
Oct 1
Layer
Model layer
Setting
Models and APIs
Evaluated models
MuQ, MusicFM
- ComponentAudio
Abstract用移调对齐的多 SAE 恢复和弦、调与旋律轨道，并用少量锚点做下游音乐理解。
作者提出一套面向音乐基础模型的结构可解释性框架：不把 SAE 特征当作孤立概念，而用半音移调把它们连成有序轨道。
Paper analysisRead analysis
Evaluation and benchmarksarXiv 2609.39473Sep 30
FAME：用反事实推理评测自主智能体的虚假记忆
提出 FAME，用反事实概念漂移评测智能体虚假记忆
arXiv
2609.39473
Published
Sep 30
Layer
Model layer
Setting
Models and APIs
Evaluated models
Llama-3B
- ComponentMemory
AbstractFAME 用反事实引起的隐状态概念漂移，在出答案前区分忠实记忆与虚假记忆。
FAME 是一个免训练的评测框架，用来判断自主智能体的记忆在虚假相关、环境偏移或知识冲突下是否已变成虚假记忆。。
Paper analysisRead analysis
AttacksarXiv 2609.38899Sep 30
SceneJail: Jailbreaking multimodal large models using video scene context
提出 SceneJail，利用视频情境上下文越狱视频多模态模型
arXiv
2609.38899
Published
Sep 30
Layer
Prompt layer
Setting
Models and APIs
Attacker
Black-box
Evaluated models
Qwen2.5-VL-7B-Instruct, Qwen2.5-VL-32B-Instruct, Qwen3-VL-8B-Instruct and others8
- AttacksJailbreaks
- TechniqueCross-modal payloads
- ComponentVideo
Paper analysisRead analysis
DefensesarXiv 2609.38645Sep 30
用探针引导微调对齐模型且不损失可监控性
用持续更新的探针做微调，降低有害性并保持线性可监测性
arXiv
2609.38645
Published
Sep 30
Layer
Training and data layer
Setting
Models and APIs
Evaluated models
Mistral 7B Instruct v0.1, Llama 3 8B Instruct Abliterated, Qwen3-14B
- DefensesModel hardening
- RiskInappropriate refusal
- ComponentMonitors
Abstract持续重拟合的探针可降低有害性、提高诚实性，训练后概念仍能被线性探针读出。
Probe-guided fine-tuning 把探针分数当作唯一对齐信号，用来推动 harmlessness 与 honesty，并检查训练后这些概念是否仍线性可读。
Paper analysisRead analysis

AI Safety Daily

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

All papers

Attack type

Attack technique

Model risks

Defense type

Impact

System type

Attacker access

Attack surface / entry point

Layer

System component

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

用路由稀疏自编码器解耦语音编码器中的语言学与副语言学信息

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

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

Moshi 全双工语音模型的情感引导遵循几何结构而非标签

STCA：研究者提出针对自动驾驶视频 VLM 的时空一致性对抗攻击

CCDF dataset: Grok Imagine, Veo 3.1, Sora 2 forge surveillance footage, ten deepfake detectors basically cannot recognize it

研究者提出读取路由 logits 的 MoE 视觉语言模型多模态安全检测器

BabelFake：面向多语言音视频 DeepFake 检测的基准数据集

面向音频深度伪造检测的任务感知联合剪枝与蒸馏框架

研究审计 Qwen2-Audio 音频越狱 AdvWave-P 的频率与解码层归因

PyINE：用可验证 Python 执行轨迹研究推理模型的捷径与监督

Thrive：面向自回归 TTS 的抗重建攻击多比特语音水印框架

OmniConfess：用 Token 级「忏悔」缓解全模态幻觉

研究系统评估循环语言模型的思维链可监控性

研究：分类后缀可提升激活探针的分布外恶意输入检测

从孤立特征到轨道：通过多重 SAE 对齐发现音乐概念

FAME：用反事实推理评测自主智能体的虚假记忆

SceneJail: Jailbreaking multimodal large models using video scene context

用探针引导微调对齐模型且不损失可监控性