AIセキュリティポータルbot

Towards Practical Robustness Analysis for DNNs based on PAC-Model Learning

Authors: Renjue Li, Pengfei Yang, Cheng-Chao Huang, Youcheng Sun, Bai Xue, Lijun Zhang | Published: 2021-01-25 | Updated: 2022-04-13
PACロバスト性
性能評価指標
深層学習技術

Debiasing Pre-trained Contextualised Embeddings

Authors: Masahiro Kaneko, Danushka Bollegala | Published: 2021-01-23
AIによる出力のバイアスの検出
公平性のあるAIモデルの作成
深層学習手法

Generating Black-Box Adversarial Examples in Sparse Domain

Authors: Hadi Zanddizari, Behnam Zeinali, J. Morris Chang | Published: 2021-01-22 | Updated: 2021-10-15
性能評価
敵対的サンプル
敵対的攻撃

Game-Theoretic and Machine Learning-based Approaches for Defensive Deception: A Survey

Authors: Mu Zhu, Ahmed H. Anwar, Zelin Wan, Jin-Hee Cho, Charles Kamhoua, Munindar P. Singh | Published: 2021-01-21 | Updated: 2021-05-08
ゲーム理論
サイバーセキュリティ
防御的欺瞞

Membership Inference Attack on Graph Neural Networks

Authors: Iyiola E. Olatunji, Wolfgang Nejdl, Megha Khosla | Published: 2021-01-17 | Updated: 2021-12-18
メンバーシップ推論
性能評価
防御効果分析

Double-Adversarial Activation Anomaly Detection: Adversarial Autoencoders are Anomaly Generators

Authors: J. -P. Schulze, P. Sperl, K. Böttinger | Published: 2021-01-12 | Updated: 2024-01-14
性能評価
機械学習手法
生成的敵対ネットワーク

SHARKS: Smart Hacking Approaches for RisK Scanning in Internet-of-Things and Cyber-Physical Systems based on Machine Learning

Authors: Tanujay Saha, Najwa Aaraj, Neel Ajjarapu, Niraj K. Jha | Published: 2021-01-07 | Updated: 2022-10-19
攻撃タイプ
機械学習手法
脆弱性管理

Machine Learning on Cloud with Blockchain: A Secure, Verifiable and Fair Approach to Outsource the Linear Regression for Data Analysis

Authors: Hanlin Zhang, Peng Gao, Jia Yu, Jie Lin, Neal N. Xiong | Published: 2021-01-07 | Updated: 2021-11-22
ブロックチェーン技術
機械学習手法
線形モデル

FLAME: Taming Backdoors in Federated Learning (Extended Version 1)

Authors: Thien Duc Nguyen, Phillip Rieger, Huili Chen, Hossein Yalame, Helen Möllering, Hossein Fereidooni, Samuel Marchal, Markus Miettinen, Azalia Mirhoseini, Shaza Zeitouni, Farinaz Koushanfar, Ahmad-Reza Sadeghi, Thomas Schneider | Published: 2021-01-06 | Updated: 2023-08-05
バックドア攻撃手法
ポイズニング
防御効果分析

Local Competition and Stochasticity for Adversarial Robustness in Deep Learning

Authors: Konstantinos P. Panousis, Sotirios Chatzis, Antonios Alexos, Sergios Theodoridis | Published: 2021-01-04 | Updated: 2021-03-29
ポイズニング
モデル性能評価
深層学習手法