R.I.P.
๐ป
Ghosted
Flareon: Stealthy any2any Backdoor Injection via Poisoned Augmentation
December 20, 2022 ยท Entered Twilight ยท ๐ arXiv.org
Repo contents: .gitignore, LICENSE, README.md, asset, augment, config.py, model, network, requirements.txt, test.py, train.py, train_learn.py, utils
Authors
Tianrui Qin, Xianghuan He, Xitong Gao, Yiren Zhao, Kejiang Ye, Cheng-Zhong Xu
arXiv ID
2212.09979
Category
cs.CR: Cryptography & Security
Cross-listed
cs.CV
Citations
3
Venue
arXiv.org
Repository
https://github.com/lafeat/flareon
โญ 6
Last Checked
3 months ago
Abstract
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 previously unexplored avenues to code-inject malicious backdoors in deep neural network models. This paper proposes Flareon, a small, stealthy, seemingly harmless code modification that specifically targets the data augmentation pipeline with motion-based triggers. Flareon neither alters ground-truth labels, nor modifies the training loss objective, nor does it assume prior knowledge of the victim model architecture, training data, and training hyperparameters. Yet, it has a surprisingly large ramification on training -- models trained under Flareon learn powerful target-conditional (or "any2any") backdoors. The resulting models can exhibit high attack success rates for any target choices and better clean accuracies than backdoor attacks that not only seize greater control, but also assume more restrictive attack capabilities. We also demonstrate the effectiveness of Flareon against recent defenses. Flareon is fully open-source and available online to the deep learning community: https://github.com/lafeat/flareon.
Community Contributions
Found the code? Know the venue? Think something is wrong? Let us know!
๐ Similar Papers
In the same crypt โ Cryptography & Security
R.I.P.
๐ป
Ghosted
The Limitations of Deep Learning in Adversarial Settings
R.I.P.
๐ป
Ghosted
Distillation as a Defense to Adversarial Perturbations against Deep Neural Networks
R.I.P.
๐ป
Ghosted
Spectre Attacks: Exploiting Speculative Execution
R.I.P.
๐ป
Ghosted
How To Backdoor Federated Learning
R.I.P.
๐ป
Ghosted