AI Total: Analyzing Security ML Models with Imperfect Data in Production
Authors: Awalin Sopan, Konstantin Berlin | Published: 2021-10-13
Poison Forensics: Traceback of Data Poisoning Attacks in Neural Networks
Authors: Shawn Shan, Arjun Nitin Bhagoji, Haitao Zheng, Ben Y. Zhao | Published: 2021-10-13 | Updated: 2022-06-15
Infinitely Divisible Noise in the Low Privacy Regime
Authors: Rasmus Pagh, Nina Mesing Stausholm | Published: 2021-10-13 | Updated: 2022-03-07
Not all noise is accounted equally: How differentially private learning benefits from large sampling rates
Authors: Friedrich Dörmann, Osvald Frisk, Lars Nørvang Andersen, Christian Fischer Pedersen | Published: 2021-10-12
On the Security Risks of AutoML
Authors: Ren Pang, Zhaohan Xi, Shouling Ji, Xiapu Luo, Ting Wang | Published: 2021-10-12
Datasets are not Enough: Challenges in Labeling Network Traffic
Authors: Jorge Guerra, Carlos Catania, Eduardo Veas | Published: 2021-10-12 | Updated: 2021-12-30
Sharing FANCI Features: A Privacy Analysis of Feature Extraction for DGA Detection
Authors: Benedikt Holmes, Arthur Drichel, Ulrike Meyer | Published: 2021-10-12
Generalization Techniques Empirically Outperform Differential Privacy against Membership Inference
Authors: Jiaxiang Liu, Simon Oya, Florian Kerschbaum | Published: 2021-10-11
The Skellam Mechanism for Differentially Private Federated Learning
Authors: Naman Agarwal, Peter Kairouz, Ziyu Liu | Published: 2021-10-11 | Updated: 2021-10-29
Adversarial Attacks in a Multi-view Setting: An Empirical Study of the Adversarial Patches Inter-view Transferability
Authors: Bilel Tarchoun, Ihsen Alouani, Anouar Ben Khalifa, Mohamed Ali Mahjoub | Published: 2021-10-10