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

Oct 12 · Monday

All papers

Found 11 papers

Filter3

Attack type

Detection evasion3

Defense type

Detection and filtering3

Impact

Output manipulation6

System type

Models and APIs11 coding agent0

Attack surface / entry point

Images, audio and video7

Layer

Prompt layer6 Model layer4

System component

MCP and skills24 Memory11 Guardrails and judges91 Monitors48 Reasoning chains62 Permissions and sandboxing12 Fine-tuning and open weights58 Vision97 Audio32 Video11 Image generation46 Embeddings4 Multimodal176

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 type：Models and APIs System type：coding agent System component：Video Clear all

Another 265papers 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
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
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
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
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 2608.18607Aug 19
VA-Judger：面向联合视频-音频生成的人类偏好反馈奖励建模
提出 VA-Judger，用人类偏好训练联合音视频奖励模型
arXiv
2608.18607
Published
Aug 19
Layer
Training and data layer
Setting
Models and APIs
Evaluated models
VA-Judger, LTX-2 + VA-Judger
- DefensesModel hardening
- RiskReward hacking
- ComponentGuardrails and judges
AbstractVA-Judger 用易到难的人类偏好学习做联合音视频奖励，并用于 LTX-2 后训练。
VA-Judger 是面向联合音视频生成的思维链全模态奖励模型，用来替代由分维度专家指标拼成的强化学习奖励。
Paper analysisRead analysis
DefensesarXiv 2607.13336Jul 15
TC-UAP：针对图像转视频与微调定制的通用视频保护方法
提出 TC-UAP，用身份级多帧扰动保护视频免被定制复现身份
arXiv
2607.13336
Published
Jul 15
Layer
Prompt layer
Setting
Models and APIs
Evaluated models
LTX-2.3, Wan2.2-5B
- ComponentVideo
AbstractTC-UAP 以可复用的时间一致扰动干扰两类定制共用的 VAE 隐空间。
作者要解决的是：发布前如何给视频加不可见扰动，使片段既不能被拿去微调视频扩散模型，也不能被抽帧做 image-to-video。
Paper analysisRead analysis
Evaluation and benchmarksarXiv 2605.18984May 19
Artifact-Bench：评估 MLLM 检测与诊断 AI 生成视频伪影
提出 Artifact-Bench，评测 MLLM 检测并诊断 AI 生成视频伪影
arXiv
2605.18984
Published
May 19
Layer
Model layer
Setting
Models and APIs
Evaluated models
Gemini 3.1 Pro, Gemini 3 Flash, Qwen3-VL 8B-Instruct and others19
- DefensesDetection and filtering
- ComponentVideo
AbstractArtifact-Bench 以三项任务评 MLLM 的 AIGC 伪影感知。
Artifact-Bench 用来看 MLLM 能否发现 AI 生成视频中的伪影，并说明视频为何不真实。
Paper analysisRead analysis
Evaluation and benchmarksarXiv 2602.10639Feb 11
VideoSTF 揭示视频大模型输出重复问题
提出 VIDEO STF 评测视频大模型输出重复并压力测试时序扰动
arXiv
2602.10639
Published
Feb 11
Layer
Prompt layer
Setting
Models and APIs
Evaluated models
LLaVA-Video-7B-Qwen2, LLaVA-Video-7B-Qwen2-Video-Only, LLaVA-NeXT-Video-7B and others10
- AttacksDenial of service
- ComponentVideo
AbstractVIDEO STF 把输出重复做成可测、可被时间扰动放大、并可黑盒诱导的失败。
VIDEO STF 测量 VideoLLM 的输出重复，并把时间变换用作 black-box 诱导。
Paper analysisRead analysis
Evaluation and benchmarksarXiv 2512.03992Dec 4, 2025
DIQ-H 基准与 VGIR 框架：评估 VLM 在对抗视觉条件下的鲁棒性
提出 DIQ-H 基准，评测 VLM 在连续退化视觉流中的幻觉残留与恢复
arXiv
2512.03992
Published
Dec 4, 2025
Layer
Model layer
Setting
Models and APIs
Evaluated models
LLaVA-7B-strict, InternVL2-8B-strict, Phi-3-Vision-strict and others17
- RiskHallucination and fabrication
- ComponentVideo
AbstractDIQ-H 用连续退化视频测幻觉延续与恢复，VIR 用不确定性过滤生成伪标注。
DIQ-H 评测 VLM 在连续视觉退化中的幻觉、恢复和跨时间一致性。VIR 用轻量模型的不确定性过滤生成伪真值。
Paper analysisRead analysis

You have reached the end

AI Safety Daily

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