paper-with-me

Papers

Augmentation Backdoors

2022-09-29 · Joseph Rance, Yiren Zhao, Ilia Shumailov, Robert Mullins

Data augmentation is used extensively to improve model generalisation. However, reliance on external libraries to implement augmentation methods introduces a vulnerability into the machine learning pipeline. It is well known that backdoors can be inserted into machine learning models through serving a modified dataset to train on. Augmentation therefore presents a perfect opportunity to perform this modification without requiring an initially backdoored dataset. In this paper we present three backdoor attacks that can be covertly inserted into data augmentation. Our attacks each insert a backdoor using a different type of computer vision augmentation transform, covering simple image transforms, GAN-based augmentation, and composition-based augmentation. By inserting the backdoor using these augmentation transforms, we make our backdoors difficult to detect, while still supporting arbitrary backdoor functionality. We evaluate our attacks on a range of computer vision benchmarks and demonstrate that an attacker is able to introduce backdoors through just a malicious augmentation routine.

📄 PDF Abstract BibTeX arXiv:2209.15139

Code (1)

slkdfjslkjfd/augmentation_backdoors 공식 구현 pytorch

Tasks

Data Augmentation

Similar Papers 제목 키워드 기반

Assessing the Operational Impact of Poisoning Attacks over Augmented 3D Point Cloud Public Datasets for Connected and Autonomous Vehicles

2026-07-07 · Marwan Lazrag, Badis Hammi, Lorena Gonzalez-Manzano, Joaquin Garcia-Alfaro arxiv

Poisoning attacks against public datasets lead to major concerns, such as (i) misclassification of perceived objects when the poisoned data is used for training and (ii) embedding of backdoors that may eventually be trig…

Autonomous VehiclesData Augmentation

Flareon: Stealthy any2any Backdoor Injection via Poisoned Augmentation

2022-12-20 · Tianrui Qin, Xianghuan He, Xitong Gao, Yiren Zhao 외

Open software supply chain attacks, once successful, can exact heavy costs in mission-critical applications. As open-source ecosystems for deep learning flourish and become increasingly universal, they present attackers …

Data Augmentation

SanitAIs: Unsupervised Data Augmentation to Sanitize Trojaned Neural Networks

2021-09-09 · Kiran Karra, Chace Ashcraft, Cash Costello

Self-supervised learning (SSL) methods have resulted in broad improvements to neural network performance by leveraging large, untapped collections of unlabeled data to learn generalized underlying structure. In this work…

Data AugmentationSelf-Supervised Learning

Backdoor Vulnerabilities in Normally Trained Deep Learning Models

2022-11-29 · Guanhong Tao, Zhenting Wang, Siyuan Cheng, Shiqing Ma 외

We conduct a systematic study of backdoor vulnerabilities in normally trained Deep Learning models. They are as dangerous as backdoors injected by data poisoning because both can be equally exploited. We leverage 20 diff…

Data PoisoningDeep Learning

Detecting Backdoors in Neural Networks Using Novel Feature-Based Anomaly Detection

2020-11-04 · Hao Fu, Akshaj Kumar Veldanda, Prashanth Krishnamurthy, Siddharth Garg 외

This paper proposes a new defense against neural network backdooring attacks that are maliciously trained to mispredict in the presence of attacker-chosen triggers. Our defense is based on the intuition that the feature …

Anomaly DetectionData Augmentation