Making machine learning robust against adversarial inputs

2018/06/25 by Ian Goodfellow, Patrick McDaniel, Nicolas Papernot · 29 citations
Computer Science · #Adversarial Robustness in Machine Learning #Anomaly Detection Techniques and Applications #Advanced Malware Detection Techniques

paper · pdf · doi:10.1145/3134599

Abstract

Such inputs distort how machine-learning-based systems are able to function in the world as it is.

Cited by

• Spatially Correlated Patterns in Adversarial Images
• Pruning Graphs by Adversarial Robustness Evaluation to Strengthen GNN Defenses
• The Security of Smart Buildings: a Systematic Literature Review
• SPADE: A Spectral Method for Black-Box Adversarial Robustness Evaluation
• Improved robustness to adversarial examples using Lipschitz regularization of the loss
• Defending SVMs against Poisoning Attacks: the Hardness and DBSCAN\n Approach
• SEALing Neural Network Models in Secure Deep Learning Accelerators
• Online Robust Regression via SGD on the l1 loss
• A.I. Robustness: a Human-Centered Perspective on Technological Challenges and Opportunities
• Real Preferences Under Arbitrary Norms
• Dynamic Algorithmic Service Agreements Perspective
• Enhancing the Robustness of Deep Neural Networks by Boundary Conditional GAN
• Understanding Adversarial Robustness: The Trade-off between Minimum and Average Margin
• An Algorithm for Out-Of-Distribution Attack to Neural Network Encoder
• A Bayes-Optimal View on Adversarial Examples
• Security in Brain-Computer Interfaces
• Adversarial Recommendation: Attack of the Learned Fake Users
• Evidence for the intrinsically nonlinear nature of receptive fields in vision. [europepmc]
• Mimicking Anti-Viruses with Machine Learning and Entropy Profiles. [europepmc]
• Deep ConvNet: Non-Random Weight Initialization for Repeatable Determinism, Examined with FSGM. [europepmc]
• Delta Variant with P681R Critical Mutation Revealed by Ultra-Large Atomic-Scale Ab Initio Simulation: Implications for the Fundamentals of Biomolecular Interactions. [europepmc]
• Understanding Is a Process. [europepmc]
• On the synthesis of visual illusions using deep generative models. [europepmc]
• Assessment of Physical Fitness and Health Status of Athletes Based on Intelligent Medical Treatment under Machine Learning. [europepmc]
• Research on a Machine Learning-Based Method for Assessing the Safety State of Historic Buildings. [europepmc]
• A Literature Survey on AI-Aided Beamforming and Beam Management for 5G and 6G Systems. [europepmc]
• Investigating whether deep learning models for co-folding learn the physics of protein-ligand interactions. [europepmc]
• Trustworthy AI for medical decisions: Adversarially robust and fair machine learning prediction for Parkinson's disease. [europepmc]
• Integrating natural language processing into radiation oncology: a practical guide to transformer architecture and large language models. [europepmc]

Related

• Trustworthy Machine Learning under Social and Adversarial Data Sources
• Machine Learning and the Future of Realism
• Security Matters: A Survey on Adversarial Machine Learning
• Adversarial ML Problems Are Getting Harder to Solve and to Evaluate
• Unrestricted Adversarial Examples