AIセキュリティポータルbot

How Does a Deep Learning Model Architecture Impact Its Privacy? A Comprehensive Study of Privacy Attacks on CNNs and Transformers

Authors: Guangsheng Zhang, Bo Liu, Huan Tian, Tianqing Zhu, Ming Ding, Wanlei Zhou | Published: 2022-10-20 | Updated: 2024-02-02
プライバシーリスク管理
ポイズニング
メンバーシップ推論

A Comprehensive Survey on Edge Data Integrity Verification: Fundamentals and Future Trends

Authors: Yao Zhao, Youyang Qu, Yong Xiang, Md Palash Uddin, Dezhong Peng, Longxiang Gao | Published: 2022-10-20 | Updated: 2024-08-07
セキュリティ分析
プライバシーリスク管理
計算効率

Canary in a Coalmine: Better Membership Inference with Ensembled Adversarial Queries

Authors: Yuxin Wen, Arpit Bansal, Hamid Kazemi, Eitan Borgnia, Micah Goldblum, Jonas Geiping, Tom Goldstein | Published: 2022-10-19 | Updated: 2023-06-01
プライバシー評価
メンバーシップ開示リスク
敵対的攻撃手法

An Empirical Analysis of SMS Scam Detection Systems

Authors: Muhammad Salman, Muhammad Ikram, Mohamed Ali Kaafar | Published: 2022-10-19
メンバーシップ推論
性能評価
敵対的攻撃手法

Differentially Private Diffusion Models

Authors: Tim Dockhorn, Tianshi Cao, Arash Vahdat, Karsten Kreis | Published: 2022-10-18 | Updated: 2023-12-31
プライバシー評価
性能評価
生成的敵対ネットワーク

MaSS: Multi-attribute Selective Suppression

Authors: Chun-Fu Chen, Shaohan Hu, Zhonghao Shi, Prateek Gulati, Bill Moriarty, Marco Pistoia, Vincenzo Piuri, Pierangela Samarati | Published: 2022-10-18 | Updated: 2022-10-24
データプライバシー評価
ポイズニング
性能評価

Scaling Adversarial Training to Large Perturbation Bounds

Authors: Sravanti Addepalli, Samyak Jain, Gaurang Sriramanan, R. Venkatesh Babu | Published: 2022-10-18
敵対的サンプル
敵対的攻撃手法
深層学習手法

DPIS: An Enhanced Mechanism for Differentially Private SGD with Importance Sampling

Authors: Jianxin Wei, Ergute Bao, Xiaokui Xiao, Yin Yang | Published: 2022-10-18 | Updated: 2024-08-01
プライバシー分析
プライバシー評価
深層学習手法

Towards Generating Adversarial Examples on Mixed-type Data

Authors: Han Xu, Menghai Pan, Zhimeng Jiang, Huiyuan Chen, Xiaoting Li, Mahashweta Das, Hao Yang | Published: 2022-10-17
敵対的サンプル
敵対的攻撃手法
最適化アルゴリズムの選択と評価

Marksman Backdoor: Backdoor Attacks with Arbitrary Target Class

Authors: Khoa D. Doan, Yingjie Lao, Ping Li | Published: 2022-10-17
バックドア攻撃
性能評価