モデル性能評価

Identifying Untrustworthy Predictions in Neural Networks by Geometric Gradient Analysis

Authors: Leo Schwinn, An Nguyen, René Raab, Leon Bungert, Daniel Tenbrinck, Dario Zanca, Martin Burger, Bjoern Eskofier | Published: 2021-02-24
モデル性能評価
信頼評価モジュール
敵対的サンプルの検知

A Zeroth-Order Block Coordinate Descent Algorithm for Huge-Scale Black-Box Optimization

Authors: HanQin Cai, Yuchen Lou, Daniel McKenzie, Wotao Yin | Published: 2021-02-21 | Updated: 2021-06-11
ウォーターマーキング
モデル性能評価
信号解析

IoTDevID: A Behavior-Based Device Identification Method for the IoT

Authors: Kahraman Kostas, Mike Just, Michael A. Lones | Published: 2021-02-17 | Updated: 2022-07-19
データセット評価
データ収集
モデル性能評価

ppAURORA: Privacy Preserving Area Under Receiver Operating Characteristic and Precision-Recall Curves

Authors: Ali Burak Ünal, Nico Pfeifer, Mete Akgün | Published: 2021-02-17 | Updated: 2023-06-15
ウォーターマーキング
データ保護手法
モデル性能評価

Towards Certifying L-infinity Robustness using Neural Networks with L-inf-dist Neurons

Authors: Bohang Zhang, Tianle Cai, Zhou Lu, Di He, Liwei Wang | Published: 2021-02-10 | Updated: 2021-06-14
データセット評価
モデル性能評価
敵対的サンプル

“What’s in the box?!”: Deflecting Adversarial Attacks by Randomly Deploying Adversarially-Disjoint Models

Authors: Sahar Abdelnabi, Mario Fritz | Published: 2021-02-09 | Updated: 2021-03-09
ポイズニング
モデル性能評価
攻撃手法

$k$-Anonymity in Practice: How Generalisation and Suppression Affect Machine Learning Classifiers

Authors: Djordje Slijepčević, Maximilian Henzl, Lukas Daniel Klausner, Tobias Dam, Peter Kieseberg, Matthias Zeppelzauer | Published: 2021-02-09 | Updated: 2022-06-22
データセット評価
データ保護手法
モデル性能評価

Protecting Intellectual Property of Generative Adversarial Networks from Ambiguity Attack

Authors: Ding Sheng Ong, Chee Seng Chan, Kam Woh Ng, Lixin Fan, Qiang Yang | Published: 2021-02-08 | Updated: 2021-03-01
ウォーターマーキング
データ保護手法
モデル性能評価

Optimal Transport as a Defense Against Adversarial Attacks

Authors: Quentin Bouniot, Romaric Audigier, Angélique Loesch | Published: 2021-02-05 | Updated: 2021-03-30
モデル性能評価
攻撃手法
敵対的訓練

ML-Doctor: Holistic Risk Assessment of Inference Attacks Against Machine Learning Models

Authors: Yugeng Liu, Rui Wen, Xinlei He, Ahmed Salem, Zhikun Zhang, Michael Backes, Emiliano De Cristofaro, Mario Fritz, Yang Zhang | Published: 2021-02-04 | Updated: 2021-10-06
ポイズニング
メンバーシップ推論
モデル性能評価