Effective Ambiguity Attack Against Passport-based DNN Intellectual Property Protection Schemes through Fully Connected Layer Substitution
通过全连接层替换对基于护照的 DNN 知识产权保护方案进行有效的模糊攻击
Progressive Open Space Expansion for Open-Set Model Attribution
开放集模型归因的渐进式开放空间扩展
Breaching FedMD: Image Recovery via Paired-Logits Inversion Attack
违反 FedMD:通过 Paired-Logits 反转攻击恢复图像
DartBlur: Privacy Preservation with Detection Artifact Suppression
DartBlur:通过检测伪影抑制实现隐私保护
Reinforcement Learning-based Black-Box Model Inversion Attacks
基于强化学习的黑盒模型反转攻击
Model-Agnostic Gender Debiased Image Captioning
与模型无关的性别偏差图像标题
Uncurated Image-Text Datasets: Shedding Light on Demographic Bias
未经整理的图像文本数据集:揭示人口统计偏见
AltFreezing for more General Video Face Forgery Detection
AltFreezing 用于更通用的视频人脸伪造检测
Make Landscape Flatter in Differentially Private Federated Learning
让差异化私有联邦学习的景观更加平坦
DynaFed: Tackling Client Data Heterogeneity with Global Dynamics
DynaFed:通过全局动态解决客户数据异构性
Re-Thinking Model Inversion Attacks Against Deep Neural Networks
重新思考针对深度神经网络的模型反转攻击
Safe Latent Diffusion: Mitigating Inappropriate Degeneration in Diffusion Models
安全潜在扩散:减轻扩散模型中的不适当退化
TrojViT: Trojan Insertion in Vision Transformers
TrojViT:Vision Transformers 中的木马插入
Difficulty-based Sampling for Debiased Contrastive Representation Learning
用于无偏差对比表示学习的基于难度的采样
Model Barrier: A Compact Un-Transferable Isolation Domain for Model Intellectual Property Protection
Model Barrier:用于模型知识产权保护的紧凑型不可转移隔离域
Fair Scratch Tickets: Finding Fair Sparse Networks without Weight Training
公平刮奖券:无需重量训练即可找到公平的稀疏网络
CLIP2Protect: Protecting Facial Privacy using Text-Guided Makeup via Adversarial Latent Search
CLIP2Protect:通过对抗性潜在搜索使用文本引导化妆保护面部隐私
Bias in Pruned Vision Models: In-Depth Analysis and Countermeasures
修剪视觉模型中的偏差:深入分析和对策
Learning to Generate Image Embeddings with User-Level Differential Privacy
学习使用用户级差分隐私生成图像嵌入
Bias Mimicking: A Simple Sampling Approach for Bias Mitigation
偏差模仿:一种减轻偏差的简单采样方法
CaPriDe Learning: Confidential and Private Decentralized Learning based on Encryption-Friendly Distillation Loss
CaPriDe Learning:基于加密友好蒸馏损失的保密私密去中心化学习
DeAR: Debiasing Vision-Language Models with Additive Residuals
DeAR:使用可加残差消除视觉语言模型的偏差
Deep Deterministic Uncertainty: A New Simple Baseline
深度确定性不确定性:新的简单基线
Manipulating Transfer Learning for Property Inference
操纵迁移学习进行属性推理
Training Debiased Subnetworks with Contrastive Weight Pruning
通过对比权重剪枝训练去偏子网络
Diffusion Art or Digital Forgery? Investigating Data Replication in Diffusion Models
扩散艺术还是数字伪造? 研究扩散模型中的数据复制
STDLens: Model Hijacking-Resilient Federated Learning for Object Detection
STDLens:用于对象检测的模型劫持弹性联合学习
Architectural Backdoors in Neural Networks
神经网络中的架构后门
MEDIC: Remove Model Backdoors via Importance Driven Cloning
MEDIC:通过重要性驱动克隆删除模型后门
Learning Debiased Representations via Conditional Attribute Interpolation
通过条件属性插值学习去偏表示
猜您喜欢
推荐内容
开源项目推荐 更多
热门活动
热门器件
用户搜过
随便看看
热门下载
热门文章
热门标签
评论