# Non-Negative Networks Against Adversarial Attacks

arXiv: https://arxiv.org/abs/1806.06108 · HTML: https://mlsanity.com/paper/1806.06108/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Jun 2018.

## Built on by (most cited first, 20 of 20)

- [Reasoning Robustness of LLMs to Adversarial Typographical Errors](https://mlsanity.com/paper/2411.05345/) (2024)
- [RS-Del: Edit Distance Robustness Certificates for Sequence Classifiers via Randomized Deletion](https://mlsanity.com/paper/2302.01757/) (2023)
- [MERLIN -- Malware Evasion with Reinforcement LearnINg](https://mlsanity.com/paper/2203.12980/) (2022)
- [A Survey on Malware Detection with Graph Representation Learning](https://mlsanity.com/paper/2303.16004/) (2023)
- [Reproducibility in Multiple Instance Learning: A Case For Algorithmic Unit Tests](https://mlsanity.com/paper/2310.17867/) (2023)
- [Malware Analysis with Artificial Intelligence and a Particular Attention on Results Interpretability](https://mlsanity.com/paper/2107.11100/) (2021)
- [Provably Tightest Linear Approximation for Robustness Verification of Sigmoid-like Neural Networks](https://mlsanity.com/paper/2208.09872/) (2022)
- [Asymmetric Certified Robustness via Feature-Convex Neural Networks](https://mlsanity.com/paper/2302.01961/) (2023)
- [Single-Shot Black-Box Adversarial Attacks Against Malware Detectors: A Causal Language Model Approach](https://mlsanity.com/paper/2112.01724/) (2021)
- [A Robust Defense against Adversarial Attacks on Deep Learning-based Malware Detectors via (De)Randomized Smoothing](https://mlsanity.com/paper/2402.15267/) (2024)
- [Mal2GCN: A Robust Malware Detection Approach Using Deep Graph Convolutional Networks With Non-Negative Weights](https://mlsanity.com/paper/2108.12473/) (2021)
- [DRSM: De-Randomized Smoothing on Malware Classifier Providing Certified Robustness](https://mlsanity.com/paper/2303.13372/) (2023)
- [You Don't Need Robust Machine Learning to Manage Adversarial Attack Risks](https://mlsanity.com/paper/2306.09951/) (2023)
- [Living off the Analyst: Harvesting Features from Yara Rules for Malware Detection](https://mlsanity.com/paper/2411.18516/) (2024)
- [Stop Walking in Circles! Bailing Out Early in Projected Gradient Descent](https://mlsanity.com/paper/2503.19347/) (2025)
- [On the Security Risks of ML-based Malware Detection Systems: A Survey](https://mlsanity.com/paper/2505.10903/) (2025)
- [Multi-view Representation Learning from Malware to Defend Against Adversarial Variants](https://mlsanity.com/paper/2210.15429/) (2022)
- [DualApp: Tight Over-Approximation for Neural Network Robustness Verification via Under-Approximation](https://mlsanity.com/paper/2211.11186/) (2022)
- [Certified Adversarial Robustness of Machine Learning-based Malware Detectors via (De)Randomized Smoothing](https://mlsanity.com/paper/2405.00392/) (2024)
- [Adversarial Samples Are Not Created Equal](https://mlsanity.com/paper/2601.00577/) (2026)

## Abstract (arXiv)

Adversarial attacks against neural networks are a problem of considerable importance, for which effective defenses are not yet readily available. We make progress toward this problem by showing that non-negative weight constraints can be used to improve resistance in specific scenarios. In particular, we show that they can provide an effective defense for binary classification problems with asymmetric cost, such as malware or spam detection. We also show the potential for non-negativity to be helpful to non-binary problems by applying it to image classification.