mlsanityData to 7 Oct 2026

Non-Negative Networks Against Adversarial Attacks

arXiv 1806.06108 ↗First posted 15 Jun 2018stat.ML cs.AI cs.LGcited by 20

Not on the map. Why?

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.

Key facts. Cited by 20 papers in the map (data through 7 Oct 2026). First posted on arXiv 15 Jun 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 3; 2022: 4; 2023: 6; 2024: 4; 2025: 2; 2026: 1.

20 papers.

Sort:

By area:

  1. 2024Reasoning Robustness of LLMs to Adversarial Typographical Errorscited by 31
  2. 2023RS-Del: Edit Distance Robustness Certificates for Sequence Classifiers via Randomized Deletioncited by 17
  3. 2023A Survey on Malware Detection with Graph Representation Learningcited by 11
  4. 2023Reproducibility in Multiple Instance Learning: A Case For Algorithmic Unit Testscited by 11
  5. 2022MERLIN -- Malware Evasion with Reinforcement LearnINgcited by 10
  6. 2021Malware Analysis with Artificial Intelligence and a Particular Attention on Results Interpretabilitycited by 9
  7. 2022Provably Tightest Linear Approximation for Robustness Verification of Sigmoid-like Neural Networkscited by 8
  8. 2023Asymmetric Certified Robustness via Feature-Convex Neural Networkscited by 8
  9. 2021Single-Shot Black-Box Adversarial Attacks Against Malware Detectors: A Causal Language Model Approachcited by 4
  10. 2024A Robust Defense against Adversarial Attacks on Deep Learning-based Malware Detectors via (De)Randomized Smoothingcited by 4
  11. 2021Mal2GCN: A Robust Malware Detection Approach Using Deep Graph Convolutional Networks With Non-Negative Weightscited by 3
  12. 2023DRSM: De-Randomized Smoothing on Malware Classifier Providing Certified Robustnesscited by 3
8 more
  1. 2023You Don't Need Robust Machine Learning to Manage Adversarial Attack Riskscited by 3
  2. 2024Living off the Analyst: Harvesting Features from Yara Rules for Malware Detectioncited by 3
  3. 2025Stop Walking in Circles! Bailing Out Early in Projected Gradient Descentcited by 2
  4. 2025On the Security Risks of ML-based Malware Detection Systems: A Surveycited by 1
  5. 2022Multi-view Representation Learning from Malware to Defend Against Adversarial Variantscited by 0
  6. 2022DualApp: Tight Over-Approximation for Neural Network Robustness Verification via Under-Approximationcited by 0
  7. 2024Certified Adversarial Robustness of Machine Learning-based Malware Detectors via (De)Randomized Smoothingcited by 0
  8. 2026Adversarial Samples Are Not Created Equalcited by 0