AIセキュリティポータルbot

SUIS: An Online Graphical Signature-Based User Identification System

Authors: Shahid Alam | Published: 2016-05-29
デジタル署名と機械学習の統合
モデル性能評価
ユーザー識別システム

Data-driven software security: Models and methods

Authors: Úlfar Erlingsson | Published: 2016-05-27
セキュリティ保証
プライバシー保護メカニズム
脆弱性管理

Deep Structured Energy Based Models for Anomaly Detection

Authors: Shuangfei Zhai, Yu Cheng, Weining Lu, Zhongfei Zhang | Published: 2016-05-25 | Updated: 2016-06-16
AIによる出力の識別
モデル性能評価
モデル設計

A note on privacy preserving iteratively reweighted least squares

Authors: Mijung Park, Max Welling | Published: 2016-05-24
プライバシー保護メカニズム
プライバシー保護機械学習
差分プライバシー

Transferability in Machine Learning: from Phenomena to Black-Box Attacks using Adversarial Samples

Authors: Nicolas Papernot, Patrick McDaniel, Ian Goodfellow | Published: 2016-05-24
モデルの頑健性保証
敵対的サンプル
敵対的攻撃分析

A First Look at Ad-block Detection: A New Arms Race on the Web

Authors: Muhammad Haris Mughees, Zhiyun Qian, Zubair Shafiq, Karishma Dash, Pan Hui | Published: 2016-05-19
URLベース検出
データ収集
特徴重要性分析

On-Average KL-Privacy and its equivalence to Generalization for Max-Entropy Mechanisms

Authors: Yu-Xiang Wang, Jing Lei, Stephen E. Fienberg | Published: 2016-05-08
プライバシー保護メカニズム
差分プライバシー
情報理論

Crafting Adversarial Input Sequences for Recurrent Neural Networks

Authors: Nicolas Papernot, Patrick McDaniel, Ananthram Swami, Richard Harang | Published: 2016-04-28
敵対的サンプル
敵対的攻撃
深層学習

Finding Common Characteristics Among NBA Playoff and Championship Teams: A Machine Learning Approach

Authors: Ikjyot Singh Kohli | Published: 2016-04-18 | Updated: 2017-04-03
モデル性能評価
決定木
特徴重要度分析

A General Retraining Framework for Scalable Adversarial Classification

Authors: Bo Li, Yevgeniy Vorobeychik, Xinyun Chen | Published: 2016-04-09 | Updated: 2016-11-26
敵対的学習
敵対的攻撃
敵対的訓練