# Improving Adversarial Robustness via Guided Complement Entropy

arXiv: https://arxiv.org/abs/1903.09799 · HTML: https://mlsanity.com/paper/1903.09799/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Mar 2019.

## Built on by (most cited first, 15 of 15)

- [Advances in adversarial attacks and defenses in computer vision: A survey](https://mlsanity.com/paper/2108.00401/) (2021)
- [Inspect, Understand, Overcome: A Survey of Practical Methods for AI Safety](https://mlsanity.com/paper/2104.14235/) (2021)
- [AutoAdvExBench: Benchmarking autonomous exploitation of adversarial example defenses](https://mlsanity.com/paper/2503.01811/) (2025)
- [Adversarial Learning with Cost-Sensitive Classes](https://mlsanity.com/paper/2101.12372/) (2021)
- [Perturbation Inactivation Based Adversarial Defense for Face Recognition](https://mlsanity.com/paper/2207.06035/) (2022)
- [Improving Online Performance Prediction for Semantic Segmentation](https://mlsanity.com/paper/2104.05255/) (2021)
- [Ensemble Defense with Data Diversity: Weak Correlation Implies Strong Robustness](https://mlsanity.com/paper/2106.02867/) (2021)
- [Data-free Defense of Black Box Models Against Adversarial Attacks](https://mlsanity.com/paper/2211.01579/) (2022)
- [Artificial Immune System of Secure Face Recognition Against Adversarial Attacks](https://mlsanity.com/paper/2406.18144/) (2024)
- [Improving Self-supervised Learning for Out-of-distribution Task via Auxiliary Classifier](https://mlsanity.com/paper/2209.02881/) (2022)
- [Towards Robust 2D Convolution for Reliable Visual Recognition](https://mlsanity.com/paper/2203.09790/) (2022)
- [Robust Few-shot Learning Without Using any Adversarial Samples](https://mlsanity.com/paper/2211.01598/) (2022)
- [Adversarial Attacks and Defences for Skin Cancer Classification](https://mlsanity.com/paper/2212.06822/) (2022)
- [Analysis of Explainable Artificial Intelligence Methods on Medical Image Classification](https://mlsanity.com/paper/2212.10565/) (2022)
- [GReAT: A Graph Regularized Adversarial Training Method](https://mlsanity.com/paper/2310.05336/) (2023)

## Abstract (arXiv)

Adversarial robustness has emerged as an important topic in deep learning as carefully crafted attack samples can significantly disturb the performance of a model. Many recent methods have proposed to improve adversarial robustness by utilizing adversarial training or model distillation, which adds additional procedures to model training. In this paper, we propose a new training paradigm called Guided Complement Entropy (GCE) that is capable of achieving "adversarial defense for free," which involves no additional procedures in the process of improving adversarial robustness. In addition to maximizing model probabilities on the ground-truth class like cross-entropy, we neutralize its probabilities on the incorrect classes along with a "guided" term to balance between these two terms. We show in the experiments that our method achieves better model robustness with even better performance compared to the commonly used cross-entropy training objective. We also show that our method can be used orthogonal to adversarial training across well-known methods with noticeable robustness gain. To the best of our knowledge, our approach is the first one that improves model robustness without compromising performance.