モデルの頑健性保証

Theoretical Insights in Model Inversion Robustness and Conditional Entropy Maximization for Collaborative Inference Systems

Authors: Song Xia, Yi Yu, Wenhan Yang, Meiwen Ding, Zhuo Chen, Ling-Yu Duan, Alex C. Kot, Xudong Jiang | Published: 2025-03-01 | Updated: 2025-04-03
プライバシー保護
モデルの頑健性保証
モデル性能評価

Let the Noise Speak: Harnessing Noise for a Unified Defense Against Adversarial and Backdoor Attacks

Authors: Md Hasan Shahriar, Ning Wang, Naren Ramakrishnan, Y. Thomas Hou, Wenjing Lou | Published: 2024-06-18 | Updated: 2025-04-14
モデルの頑健性保証
再構成攻撃
敵対的攻撃検出

LookAhead: Preventing DeFi Attacks via Unveiling Adversarial Contracts

Authors: Shoupeng Ren, Lipeng He, Tianyu Tu, Di Wu, Jian Liu, Kui Ren, Chun Chen | Published: 2024-01-14 | Updated: 2025-04-02
スマートコントラクト
モデルの頑健性保証
モデル性能評価

Prediction Poisoning: Towards Defenses Against DNN Model Stealing Attacks

Authors: Tribhuvanesh Orekondy, Bernt Schiele, Mario Fritz | Published: 2019-06-26 | Updated: 2020-03-03
モデルの頑健性保証
モデル抽出攻撃の検知
攻撃の評価

On the Vulnerability of CNN Classifiers in EEG-Based BCIs

Authors: Xiao Zhang, Dongrui Wu | Published: 2019-03-31
モデルの頑健性保証
敵対的学習
敵対的攻撃検出

Bridging Adversarial Robustness and Gradient Interpretability

Authors: Beomsu Kim, Junghoon Seo, Taegyun Jeon | Published: 2019-03-27 | Updated: 2019-04-19
モデルの頑健性保証
敵対的学習
解釈可能性

A geometry-inspired decision-based attack

Authors: Yujia Liu, Seyed-Mohsen Moosavi-Dezfooli, Pascal Frossard | Published: 2019-03-26
モデルの頑健性保証
効果的な摂動手法
敵対的攻撃検出

Defending against Whitebox Adversarial Attacks via Randomized Discretization

Authors: Yuchen Zhang, Percy Liang | Published: 2019-03-25
モデルの頑健性保証
効果的な摂動手法
敵対的攻撃検出

Exploiting Excessive Invariance caused by Norm-Bounded Adversarial Robustness

Authors: Jörn-Henrik Jacobsen, Jens Behrmannn, Nicholas Carlini, Florian Tramèr, Nicolas Papernot | Published: 2019-03-25
モデルの頑健性保証
敵対的サンプルの脆弱性
敵対的攻撃検出

The LogBarrier adversarial attack: making effective use of decision boundary information

Authors: Chris Finlay, Aram-Alexandre Pooladian, Adam M. Oberman | Published: 2019-03-25
モデルの頑健性保証
効果的な摂動手法
敵対的学習