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

Oct 12 · Monday

All papers

Found 9 papers

Filter3

Attack type

Malicious use3

Defense type

Model hardening5 Inference-time intervention3 Detection and filtering4 Watermarking and provenance4

Impact

Harmful content3

System type

Models and APIs7

Attack surface / entry point

User input4 Images, audio and video3

Layer

Training and data layer4

System component

MCP and skills10 Memory5 RAG6 Guardrails and judges78 Monitors5 Reasoning chains14 Fine-tuning and open weights20 Vision22 Audio6 Video4 Image generation9 Multimodal38

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.

Defense type：Model hardening Defense type：Detection and filtering System component：Image generation Clear all

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

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 2610.06503Oct 5
研究评测五款开源文生图模型的有害内容生成与审核缺口
评测文生图模型的有害内容生成能力与审核检测缺口
arXiv
2610.06503
Published
Oct 5
Layer
Model layer
Setting
Models and APIs
Evaluated models
SDXL, Stable Diffusion 3.5 Large, FLUX.1-dev and others12
- DefensesDetection and filtering
- AttacksMalicious use
- ComponentImage generation
Paper analysisRead analysis
DefensesarXiv 2610.05870Oct 5
MBZUAI 提出可校准的真实图像认证方法
提出校准重合成方法，以生成器反演保真度认证真实图像并防御对抗扰动
arXiv
2610.05870
Published
Oct 5
Layer
Application layer
Setting
LLM applications
Attacker
White-box
- DefensesDetection and filtering
- AttacksDetection evasion
- ComponentImage generation
Abstract论文提出基于反演保真度与阈值校准的健全认证框架，在对抗扰动下维持错误率界限，并指出真实内容可认证性随生成器演进而萎缩。
Paper analysisRead analysis
DefensesarXiv 2610.05401Oct 5
AVCE：面向扩散模型可验证概念擦除的审计感知遗忘框架
提出审计感知遗忘框架 AVCE，从文本与视觉通路擦除扩散模型概念
arXiv
2610.05401
Published
Oct 5
Layer
Training and data layer
Setting
Models and APIs
Attacker
White-box, Black-box
Evaluated models
Stable Diffusion XL (SDXL), Stable Diffusion v1.5 (SD v1.5), Flux 1.0
- DefensesModel hardening
- AttacksJailbreaks
- ComponentImage generation
AbstractAVCE 在审计锚点上改两条注意力通路。
AVCE 是面向扩散模型的概念擦除方法，要让擦除经得起绕过文本条件的潜空间审计，而不只是挡住对抗提示词。
Paper analysisRead analysis
DefensesarXiv 2610.03980Oct 3
FADE：面向视频扩散模型的帧感知多概念擦除框架
提出 FADE，对文生视频模型做帧感知多概念擦除
arXiv
2610.03980
Published
Oct 3
Layer
Training and data layer
Setting
Models and APIs
Evaluated models
Wan2.1-T2V-1.3B, Wan2.1-T2V-14B, CogVideoX-2B and others4
- DefensesModel hardening
- AttacksMalicious use
- ComponentImage generation
AbstractFADE 用闭式编辑、帧感知适配器和软路由，在单骨干上擦除多概念并压低逐帧残差。
FADE 是面向文生视频扩散 Transformer 的多概念遗忘方法，用来抑制指定物体、画风、裸体、暴力、仇恨和名人身份，并尽量保持其他生成。作者要处理两件事。与帧无关的抑制会让概念在少数帧重现，片段均值会掩盖这一失败。
Paper analysisRead analysis
DefensesarXiv 2610.02967Oct 2
用偏好奖励与评分标准奖励组合后训练前沿文生图模型
组合偏好奖励与评分标准奖励后训练文生图模型以抑制奖励作弊
arXiv
2610.02967
Published
Oct 2
Layer
Training and data layer
Setting
Models and APIs
Evaluated models
FLUX.2-dev, Ideogram-4
- DefensesModel hardening
- RiskReward hacking
- ComponentImage generation
Abstract组合奖励后训练 FLUX.2-dev 与 Ideogram-4，并报告高于基座的胜率与 Elo。
作者给出一套开放域文生图后训练配方：把人类偏好奖励和 prompt 条件的 rubric 奖励合在一起，而不是换一个新优化器。问题是单一奖励盖不住用户意图。偏好模型能看整体观感，但对“是否实现每个要求”这类稀疏属性不敏感。
Paper analysisRead analysis
DefensesarXiv 2609.36099Sep 29
通过逆向蒸馏实现数据遗忘（IDU）
提出 IDU，在无保留样本时蒸馏单步生成器并抑制遗忘子集
arXiv
2609.36099
Published
Sep 29
Layer
Training and data layer
Setting
Models and APIs
Evaluated models
IDU one-step generator
- DefensesModel hardening
- ComponentImage generation
AbstractIDU 同时做单步蒸馏和数据遗忘，在 MNIST 与 CIFAR-10 上压低遗忘类生成率。
IDU 面向无条件 flow 与 score-based 教师，在蒸馏成单步生成器的同时做数据遗忘。
Paper analysisRead analysis
DefensesarXiv 2609.15799Sep 15
RAPID：面向文生图服务的实时防未授权蒸馏防御
提出 RAPID，离线把抗蒸馏扰动写入文生图解码器
arXiv
2609.15799
Published
Sep 15
Layer
Model layer
Setting
Models and APIs
Attacker
Black-box
Evaluated models
PixArt, SSD, SDXL and others4
- DefensesModel hardening
- AttacksExtraction and theft
- ComponentImage generation
Paper analysisRead analysis
DefensesarXiv 2603.01544Mar 2
RA-Det：利用鲁棒性不对称检测 AI 生成图像
提出 RA-Det，利用鲁棒性不对称检测 AI 生成图像
arXiv
2603.01544
Published
Mar 2
Layer
Application layer
Setting
LLM applications
- DefensesDetection and filtering
- AttacksMalicious use
- ComponentGuardrails and judges
AbstractRA-Det 把扰动下特征漂移差变成检测信号，平均 ACC 高于表中通用检测器，但不是每行最高。
RA-Det 是合成图像检测器，用扰动下的表示稳定性差异代替外观痕迹。
Paper analysisRead analysis

You have reached the end

AI Safety Daily

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