DNN IP Protection Method

Reconstructing Individual Data Points in Federated Learning Hardened with Differential Privacy and Secure Aggregation

Authors: Franziska Boenisch, Adam Dziedzic, Roei Schuster, Ali Shahin Shamsabadi, Ilia Shumailov, Nicolas Papernot | Published: 2023-01-09 | Updated: 2023-04-12
DNN IP Protection Method
Privacy Enhancing Technology
Poisoning

Privacy and Efficiency of Communications in Federated Split Learning

Authors: Zongshun Zhang, Andrea Pinto, Valeria Turina, Flavio Esposito, Ibrahim Matta | Published: 2023-01-04 | Updated: 2023-01-07
DNN IP Protection Method
Privacy Enhancing Technology
Optimization Methods

Backdoor Attacks Against Dataset Distillation

Authors: Yugeng Liu, Zheng Li, Michael Backes, Yun Shen, Yang Zhang | Published: 2023-01-03
DNN IP Protection Method
Backdoor Attack
Poisoning

REAP: A Large-Scale Realistic Adversarial Patch Benchmark

Authors: Nabeel Hingun, Chawin Sitawarin, Jerry Li, David Wagner | Published: 2022-12-12 | Updated: 2023-08-18
DNN IP Protection Method
Watermarking
Traffic Sign Classification

FedTracker: Furnishing Ownership Verification and Traceability for Federated Learning Model

Authors: Shuo Shao, Wenyuan Yang, Hanlin Gu, Zhan Qin, Lixin Fan, Qiang Yang, Kui Ren | Published: 2022-11-14 | Updated: 2024-03-02
DNN IP Protection Method
Watermarking
Malicious Client

Adversarial Policies Beat Superhuman Go AIs

Authors: Tony T. Wang, Adam Gleave, Tom Tseng, Kellin Pelrine, Nora Belrose, Joseph Miller, Michael D. Dennis, Yawen Duan, Viktor Pogrebniak, Sergey Levine, Stuart Russell | Published: 2022-11-01 | Updated: 2023-07-13
DNN IP Protection Method
Improvement of Learning
Classification of Malicious Actors

Proof of Unlearning: Definitions and Instantiation

Authors: Jiasi Weng, Shenglong Yao, Yuefeng Du, Junjie Huang, Jian Weng, Cong Wang | Published: 2022-10-20 | Updated: 2022-10-21
DNN IP Protection Method
Privacy Risk Management
Model editing techniques

BLADERUNNER: Rapid Countermeasure for Synthetic (AI-Generated) StyleGAN Faces

Authors: Adam Dorian Wong | Published: 2022-10-12 | Updated: 2022-10-28
DNN IP Protection Method
Security Assurance
Challenges of Generative Models

Preprocessors Matter! Realistic Decision-Based Attacks on Machine Learning Systems

Authors: Chawin Sitawarin, Florian Tramèr, Nicholas Carlini | Published: 2022-10-07 | Updated: 2023-07-20
DNN IP Protection Method
Model Extraction Attack
Adversarial Example

A Closer Look at Robustness to L-infinity and Spatial Perturbations and their Composition

Authors: Luke Rowe, Benjamin Thérien, Krzysztof Czarnecki, Hongyang Zhang | Published: 2022-10-05
DNN IP Protection Method
Model Design
Deep Learning Method