# Adaptive Attractors: A Defense Strategy against ML Adversarial Collusion Attacks

arXiv: https://arxiv.org/abs/2306.01400 · HTML: https://mlsanity.com/paper/2306.01400/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 17 of its 25 references that are in the map.
- First posted on arXiv 2 Jun 2023.

## Builds on (most cited first, 17 of 17)

- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Intriguing properties of neural networks](https://mlsanity.com/paper/1312.6199/) (2013)
- [Adversarial examples in the physical world](https://mlsanity.com/paper/1607.02533/) (2016)
- [DeepFool: a simple and accurate method to fool deep neural networks](https://mlsanity.com/paper/1511.04599/) (2015)
- [Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examples](https://mlsanity.com/paper/1802.00420/) (2018)
- [Decision-Based Adversarial Attacks: Reliable Attacks Against Black-Box Machine Learning Models](https://mlsanity.com/paper/1712.04248/) (2017)
- [HopSkipJumpAttack: A Query-Efficient Decision-Based Attack](https://mlsanity.com/paper/1904.02144/) (2019)
- [Parseval Networks: Improving Robustness to Adversarial Examples](https://mlsanity.com/paper/1704.08847/) (2017)
- [On the (Statistical) Detection of Adversarial Examples](https://mlsanity.com/paper/1702.06280/) (2017)
- [GeoDA: a geometric framework for black-box adversarial attacks](https://mlsanity.com/paper/2003.06468/) (2020)
- [Adversarial and Clean Data Are Not Twins](https://mlsanity.com/paper/1704.04960/) (2017)
- [Understanding Adversarial Training: Increasing Local Stability of Neural Nets through Robust Optimization](https://mlsanity.com/paper/1511.05432/) (2015)
- [Attacking Adversarial Attacks as A Defense](https://mlsanity.com/paper/2106.04938/) (2021)
- [Resisting Adversarial Attacks using Gaussian Mixture Variational Autoencoders](https://mlsanity.com/paper/1806.00081/) (2018)
- [Adversarial Attack on Attackers: Post-Process to Mitigate Black-Box Score-Based Query Attacks](https://mlsanity.com/paper/2205.12134/) (2022)
- [Tracing the Origin of Adversarial Attack for Forensic Investigation and Deterrence](https://mlsanity.com/paper/2301.01218/) (2022)

## Abstract (arXiv)

In the seller-buyer setting on machine learning models, the seller generates different copies based on the original model and distributes them to different buyers, such that adversarial samples generated on one buyer's copy would likely not work on other copies. A known approach achieves this using attractor-based rewriter which injects different attractors to different copies. This induces different adversarial regions in different copies, making adversarial samples generated on one copy not replicable on others. In this paper, we focus on a scenario where multiple malicious buyers collude to attack. We first give two formulations and conduct empirical studies to analyze effectiveness of collusion attack under different assumptions on the attacker's capabilities and properties of the attractors. We observe that existing attractor-based methods do not effectively mislead the colluders in the sense that adversarial samples found are influenced more by the original model instead of the attractors as number of colluders increases. Based on this observation, we propose using adaptive attractors whose weight is guided by a U-shape curve to cover the shortfalls. Experimentation results show that when using our approach, the attack success rate of a collusion attack converges to around 15% even when lots of copies are applied for collusion. In contrast, when using the existing attractor-based rewriter with fixed weight, the attack success rate increases linearly with the number of copies used for collusion.