# Adversarial Robustness in Machine Learning

**Type:** Topics  
**Canonical URL:** https://scholariq.org/topics/adversarial-robustness-in-machine-learning/

## Facts

| Field | Value |
| --- | --- |
| Description | This cluster of papers focuses on the robustness of deep learning models against adversarial attacks, exploring topics such as adversarial examples, security, uncertainty estimation, defenses, and verification. It delves into the challenges and potential solutions for ensuring the resilience of neural networks in the face of malicious inputs. |
| Domain | Physical Sciences |
| Field | Computer Science |
| OpenAlex ID | t11689 |
| Works | 81 |

## Topic papers all

Showing 15 of 81.

- [Explainable artificial intelligence: a comprehensive review](https://scholariq.org/papers/explainable-artificial-intelligence-a-comprehensive-review/)
- [Understanding adversarial attacks on deep learning based medical image analysis systems](https://scholariq.org/papers/understanding-adversarial-attacks-on-deep-learning-based-medical-image-analysis/)
- [Multi-task Learning for Detecting and Segmenting Manipulated Facial Images and Videos](https://scholariq.org/papers/multi-task-learning-for-detecting-and-segmenting-manipulated-facial-images-and/)
- [BlockDrop: Dynamic Inference Paths in Residual Networks](https://scholariq.org/papers/blockdrop-dynamic-inference-paths-in-residual-networks/)
- [Reflection Backdoor: A Natural Backdoor Attack on Deep Neural Networks](https://scholariq.org/papers/reflection-backdoor-a-natural-backdoor-attack-on-deep-neural-networks/)
- [Born Again Neural Networks](https://scholariq.org/papers/born-again-neural-networks/)
- [Don't Decay the Learning Rate, Increase the Batch Size](https://scholariq.org/papers/don-t-decay-the-learning-rate-increase-the-batch-size/)
- [Born Again Neural Networks](https://scholariq.org/papers/born-again-neural-networks-2/)
- [Adversarial Attacks in Modulation Recognition With Convolutional Neural Networks](https://scholariq.org/papers/adversarial-attacks-in-modulation-recognition-with-convolutional-neural-networks/)
- [A Review on Explainability in Multimodal Deep Neural Nets](https://scholariq.org/papers/a-review-on-explainability-in-multimodal-deep-neural-nets/)
- [DaST: Data-Free Substitute Training for Adversarial Attacks](https://scholariq.org/papers/dast-data-free-substitute-training-for-adversarial-attacks/)
- [A Deep Learning-Based Hybrid Framework for Object Detection and Recognition in Autonomous Driving](https://scholariq.org/papers/a-deep-learning-based-hybrid-framework-for-object-detection-and-recognition-in/)
- [Adversarial Attacks on Deep Neural Networks for Time Series Classification](https://scholariq.org/papers/adversarial-attacks-on-deep-neural-networks-for-time-series-classification/)
- [Explainable Artificial Intelligence (XAI) for Internet of Things: A Survey](https://scholariq.org/papers/explainable-artificial-intelligence-xai-for-internet-of-things-a-survey/)
- [Cyber Resilience in Healthcare Digital Twin on Lung Cancer](https://scholariq.org/papers/cyber-resilience-in-healthcare-digital-twin-on-lung-cancer/)

## Topic primary papers

Showing 15 of 28.

- [Understanding adversarial attacks on deep learning based medical image analysis systems](https://scholariq.org/papers/understanding-adversarial-attacks-on-deep-learning-based-medical-image-analysis/)
- [Reflection Backdoor: A Natural Backdoor Attack on Deep Neural Networks](https://scholariq.org/papers/reflection-backdoor-a-natural-backdoor-attack-on-deep-neural-networks/)
- [Born Again Neural Networks](https://scholariq.org/papers/born-again-neural-networks/)
- [Born Again Neural Networks](https://scholariq.org/papers/born-again-neural-networks-2/)
- [Adversarial Attacks in Modulation Recognition With Convolutional Neural Networks](https://scholariq.org/papers/adversarial-attacks-in-modulation-recognition-with-convolutional-neural-networks/)
- [DaST: Data-Free Substitute Training for Adversarial Attacks](https://scholariq.org/papers/dast-data-free-substitute-training-for-adversarial-attacks/)
- [Black-Box Access is Insufficient for Rigorous AI Audits](https://scholariq.org/papers/black-box-access-is-insufficient-for-rigorous-ai-audits/)
- [Boosting Adversarial Transferability via Gradient Relevance Attack](https://scholariq.org/papers/boosting-adversarial-transferability-via-gradient-relevance-attack/)
- [A Stitch in Time Saves Nine: A Train-Time Regularizing Loss for Improved Neural Network Calibration](https://scholariq.org/papers/a-stitch-in-time-saves-nine-a-train-time-regularizing-loss-for-improved-neural/)
- [Advancements in Data Augmentation and Transfer Learning:A Comprehensive Survey to Address Data Scarcity Challenges](https://scholariq.org/papers/advancements-in-data-augmentation-and-transfer-learning-a-comprehensive-survey/)
- [MEFF – A model ensemble feature fusion approach for tackling adversarial attacks in medical imaging](https://scholariq.org/papers/meff-a-model-ensemble-feature-fusion-approach-for-tackling-adversarial-attacks/)
- [Crafting transferable adversarial examples via contaminating the salient feature variance](https://scholariq.org/papers/crafting-transferable-adversarial-examples-via-contaminating-the-salient-feature/)
- [Counteracting adversarial attacks in autonomous driving](https://scholariq.org/papers/counteracting-adversarial-attacks-in-autonomous-driving/)
- [Frequency-based methods for improving the imperceptibility and transferability of adversarial examples](https://scholariq.org/papers/frequency-based-methods-for-improving-the-imperceptibility-and-transferability/)
- [A review of cyber attacks on sensors and perception systems in autonomous vehicle](https://scholariq.org/papers/a-review-of-cyber-attacks-on-sensors-and-perception-systems-in-autonomous/)

---
Source: ScholarIQ — public research metadata, principally OpenAlex. See https://scholariq.org/sources/ for provenance and https://scholariq.org/methodology/ for what these figures mean.