AIセキュリティポータルbot

6G White paper: Research challenges for Trust, Security and Privacy

Authors: Mika Ylianttila, Raimo Kantola, Andrei Gurtov, Lozenzo Mucchi, Ian Oppermann, Zheng Yan, Tri Hong Nguyen, Fei Liu, Tharaka Hewa, Madhusanka Liyanage, Ahmad Ijaz, Juha Partala, Robert Abbas, Artur Hecker, Sara Jayousi, Alessio Martinelli, Stefano Caputo, Jonathan Bechtold, Ivan Morales, Andrei Stoica, Giuseppe Abreu, Shahriar Shahabuddin, Erdal Panayirci, Harald Haas, Tanesh Kumar, Basak Ozan Ozparlak, Juha Röning | Published: 2020-04-24 | Updated: 2020-04-30
セキュアな通信チャネル
プライバシー保護技術
物理層セキュリティ

Systematic Evaluation of Backdoor Data Poisoning Attacks on Image Classifiers

Authors: Loc Truong, Chace Jones, Brian Hutchinson, Andrew August, Brenda Praggastis, Robert Jasper, Nicole Nichols, Aaron Tuor | Published: 2020-04-24
バックドア攻撃
ロバスト性分析
正則化

Adversarial Attacks and Defenses: An Interpretation Perspective

Authors: Ninghao Liu, Mengnan Du, Ruocheng Guo, Huan Liu, Xia Hu | Published: 2020-04-23 | Updated: 2020-10-07
ポイズニング
敵対的サンプル
敵対的攻撃手法

Adversarial Machine Learning in Network Intrusion Detection Systems

Authors: Elie Alhajjar, Paul Maxwell, Nathaniel D. Bastian | Published: 2020-04-23
敵対的サンプル
敵対的攻撃手法
機械学習

ArchNet: Data Hiding Model in Distributed Machine Learning System

Authors: Kaiyan Chang, Wei Jiang, Jinyu Zhan, Zicheng Gong, Weijia Pan | Published: 2020-04-23 | Updated: 2020-05-31
暗号化プロトコル
機械学習
画像処理

Digit Recognition From Wrist Movements and Security Concerns with Smart Wrist Wearable IOT Devices

Authors: Lambert T. Leong, Sean Wiere | Published: 2020-04-22
セキュリティ保証
機械学習の役割
特徴エンジニアリング

Live Trojan Attacks on Deep Neural Networks

Authors: Robby Costales, Chengzhi Mao, Raphael Norwitz, Bryan Kim, Junfeng Yang | Published: 2020-04-22 | Updated: 2020-05-27
トロイの木馬検出
攻撃手法
深層学習技術

How to compare adversarial robustness of classifiers from a global perspective

Authors: Niklas Risse, Christina Göpfert, Jan Philip Göpfert | Published: 2020-04-22 | Updated: 2020-10-15
ポイズニング
ロバスト性分析
評価手法

Neural Network Laundering: Removing Black-Box Backdoor Watermarks from Deep Neural Networks

Authors: William Aiken, Hyoungshick Kim, Simon Woo | Published: 2020-04-22
攻撃手法
知的財産保護
透かし除去技術

Discovering Imperfectly Observable Adversarial Actions using Anomaly Detection

Authors: Olga Petrova, Karel Durkota, Galina Alperovich, Karel Horak, Michal Najman, Branislav Bosansky, Viliam Lisy | Published: 2020-04-22
敵対的攻撃
最適化アルゴリズムの選択と評価
異常検知アルゴリズム