A cryptographic approach to black box adversarial machine learning

2019-06-07 · Kevin Shi, Daniel Hsu, Allison Bishop

We propose a new randomized ensemble technique with a provable security guarantee against black-box transfer attacks. Our proof constructs a new security problem for random binary classifiers which is easier to empirically verify and a reduction from the security of this new model to the security of the ensemble classifier. We provide experimental evidence of the security of our random binary classifiers, as well as empirical results of the adversarial accuracy of the overall ensemble to black-box attacks. Our construction crucially leverages hidden randomness in the multiclass-to-binary reduction.

📄 PDF Abstract BibTeX arXiv:1906.03231

Code (0)

등록된 구현이 없습니다.

Tasks

BIG-bench Machine Learning

Bridging machine learning and cryptography in defence against adversarial attacks

2018-09-05 · Olga Taran, Shideh Rezaeifar, Slava Voloshynovskiy

In the last decade, deep learning algorithms have become very popular thanks to the achieved performance in many machine learning and computer vision tasks. However, most of the deep learning architectures are vulnerable…

BIG-bench Machine Learning

Cryptographic Backdoor for Neural Networks: Boon and Bane

2025-09-25 · Anh Tu Ngo, Anupam Chattopadhyay, Subhamoy Maitra arxiv

In this paper we show that cryptographic backdoors in a neural network (NN) can be highly effective in two directions, namely mounting the attacks as well as in presenting the defenses as well. On the attack side, a care…

Adversarial Attack

Red Teaming Quantum-Resistant Cryptographic Standards: A Penetration Testing Framework Integrating AI and Quantum Security

2025-09-26 · Petar Radanliev arxiv

This study presents a structured approach to evaluating vulnerabilities within quantum cryptographic protocols, focusing on the BB84 quantum key distribution method and National Institute of Standards and Technology (NIS…

Anomaly Detection Red Teaming

Adversarial Examples from Cryptographic Pseudo-Random Generators

2018-11-15 · Sébastien Bubeck, Yin Tat Lee, Eric Price, Ilya Razenshteyn

In our recent work (Bubeck, Price, Razenshteyn, arXiv:1805.10204) we argued that adversarial examples in machine learning might be due to an inherent computational hardness of the problem. More precisely, we constructed …

Binary Classification General Classification

Privacy-Preserving Federated Learning: Integrating Zero-Knowledge Proofs in Scalable Distributed Architectures

2026-05-04 · Divya Gupta arxiv

The intersection of Artificial Intelligence (AI) and distributed systems has given rise to Federated Learning (FL), a paradigm that enables decentralized model training without compromising local data privacy. As organiz…

Federated Learning