AIセキュリティポータルbot

An Extension of Fano’s Inequality for Characterizing Model Susceptibility to Membership Inference Attacks

Authors: Sumit Kumar Jha, Susmit Jha, Rickard Ewetz, Sunny Raj, Alvaro Velasquez, Laura L. Pullum, Ananthram Swami | Published: 2020-09-17
メンバーシップ推論
機械学習

FLAME: Differentially Private Federated Learning in the Shuffle Model

Authors: Ruixuan Liu, Yang Cao, Hong Chen, Ruoyang Guo, Masatoshi Yoshikawa | Published: 2020-09-17 | Updated: 2021-03-20
プライバシー保護技術
分散学習

Distilled One-Shot Federated Learning

Authors: Yanlin Zhou, George Pu, Xiyao Ma, Xiaolin Li, Dapeng Wu | Published: 2020-09-17 | Updated: 2021-06-06
Few-Shot Learning
分散学習
通信効率

Multimodal Safety-Critical Scenarios Generation for Decision-Making Algorithms Evaluation

Authors: Wenhao Ding, Baiming Chen, Bo Li, Kim Ji Eun, Ding Zhao | Published: 2020-09-16 | Updated: 2020-12-26
データ生成
性能評価指標
深層強化学習

Hardware-Assisted Detection of Firmware Attacks in Inverter-Based Cyberphysical Microgrids

Authors: Abraham Peedikayil Kuruvila, Ioannis Zografopoulos, Kanad Basu, Charalambos Konstantinou | Published: 2020-09-16 | Updated: 2021-04-18
ハードウェア設計
マルウェア分類
脆弱性検出

The Dark (and Bright) Side of IoT: Attacks and Countermeasures for Identifying Smart Home Devices and Services

Authors: Ahmed Mohamed Hussain, Gabriele Oligeri, Thiemo Voigt | Published: 2020-09-16 | Updated: 2021-07-25
デバイス識別手法
機械学習
通信効率

Data Poisoning Attacks on Regression Learning and Corresponding Defenses

Authors: Nicolas Michael Müller, Daniel Kowatsch, Konstantin Böttinger | Published: 2020-09-15
バックドア攻撃
ポイズニング
ロバスト回帰

Puzzle Mix: Exploiting Saliency and Local Statistics for Optimal Mixup

Authors: Jang-Hyun Kim, Wonho Choo, Hyun Oh Song | Published: 2020-09-15 | Updated: 2020-12-30
データ生成
最適化アルゴリズムの選択と評価
機械学習

Private data sharing between decentralized users through the privGAN architecture

Authors: Jean-Francois Rajotte, Raymond T Ng | Published: 2020-09-14
データ生成
プライバシー保護
倫理的考慮

Robust Deep Learning Ensemble against Deception

Authors: Wenqi Wei, Ling Liu | Published: 2020-09-14
敵対的サンプル
敵対的攻撃検出
敵対的訓練