The Limitations of Model Uncertainty in Adversarial Settings
Not on the map. Why?
Abstract (arXiv)
Machine learning models are vulnerable to adversarial examples: minor perturbations to input samples intended to deliberately cause misclassification. While an obvious security threat, adversarial examples yield as well insights about the applied model itself. We investigate adversarial examples in the context of Bayesian neural network's (BNN's) uncertainty measures. As these measures are highly non-smooth, we use a smooth Gaussian process classifier (GPC) as substitute. We show that both confidence and uncertainty can be unsuspicious even if the output is wrong. Intriguingly, we find subtle differences in the features influencing uncertainty and confidence for most tasks.
Key facts. Cited by 14 papers in the map (data through 7 Oct 2026). First posted on arXiv 6 Dec 2018.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 5; 2022: 2; 2023: 4; 2024: 1; 2025: 0; 2026: 2.
14 papers.
Sort:
- 2021LiBRe: A Practical Bayesian Approach to Adversarial Detectioncited by 40
- 2021Bayesian Inference with Certifiable Adversarial Robustnesscited by 26
- 2023A Primer on Bayesian Neural Networks: Review and Debatescited by 26
- 2022On the Robustness of Bayesian Neural Networks to Adversarial Attackscited by 12
- 2021Adversarial Robustness Guarantees for Gaussian Processescited by 5
- 2021Exploiting Vulnerabilities in Deep Neural Networks: Adversarial and Fault-Injection Attackscited by 4
- 2023Adversarial Attacks Against Uncertainty Quantificationcited by 4
- 2021The Effect of Prior Lipschitz Continuity on the Adversarial Robustness of Bayesian Neural Networkscited by 3
- 2023Dynamic ensemble selection based on Deep Neural Network Uncertainty Estimation for Adversarial Robustnesscited by 2
- 2024Attacking Bayes: On the Adversarial Robustness of Bayesian Neural Networkscited by 2
- 2023A reading survey on adversarial machine learning: Adversarial attacks and their understandingcited by 1
- 2022Adversarial Example Detection in Deployed Tree Ensemblescited by 0
- 2026LiST: Lipschitz Scaling Training for Robust and Calibrated Neural Networks8 Jul 2026
- 2026How Worst-Case Are Adversarial Attacks? Linking Adversarial and Perturbation Robustness20 Jan 2026
- 2024Attacking Bayes: On the Adversarial Robustness of Bayesian Neural Networks27 Apr 2024
- 2023A Primer on Bayesian Neural Networks: Review and Debates28 Sep 2023
- 2023Adversarial Attacks Against Uncertainty Quantification19 Sep 2023
- 2023A reading survey on adversarial machine learning: Adversarial attacks and their understanding7 Aug 2023
- 2023Dynamic ensemble selection based on Deep Neural Network Uncertainty Estimation for Adversarial Robustness1 Aug 2023
- 2022On the Robustness of Bayesian Neural Networks to Adversarial Attacks13 Jul 2022
- 2022Adversarial Example Detection in Deployed Tree Ensembles27 Jun 2022
- 2021Exploiting Vulnerabilities in Deep Neural Networks: Adversarial and Fault-Injection Attacks5 May 2021
- 2021Adversarial Robustness Guarantees for Gaussian Processes7 Apr 2021
- 2021LiBRe: A Practical Bayesian Approach to Adversarial Detection27 Mar 2021
- 2021LiBRe: A Practical Bayesian Approach to Adversarial Detectioncited by 40
- 2021Bayesian Inference with Certifiable Adversarial Robustnesscited by 26
- 2023A Primer on Bayesian Neural Networks: Review and Debatescited by 26
- 2022On the Robustness of Bayesian Neural Networks to Adversarial Attackscited by 12
- 2021Adversarial Robustness Guarantees for Gaussian Processescited by 5
- 2021Exploiting Vulnerabilities in Deep Neural Networks: Adversarial and Fault-Injection Attackscited by 4
- 2023Adversarial Attacks Against Uncertainty Quantificationcited by 4
- 2021The Effect of Prior Lipschitz Continuity on the Adversarial Robustness of Bayesian Neural Networkscited by 3
- 2023Dynamic ensemble selection based on Deep Neural Network Uncertainty Estimation for Adversarial Robustnesscited by 2
- 2024Attacking Bayes: On the Adversarial Robustness of Bayesian Neural Networkscited by 2
- 2023A reading survey on adversarial machine learning: Adversarial attacks and their understandingcited by 1
- 2022Adversarial Example Detection in Deployed Tree Ensemblescited by 0
12 most cited of 14 All 14 (JSON)
- 2026LiST: Lipschitz Scaling Training for Robust and Calibrated Neural Networks8 Jul 2026
- 2026How Worst-Case Are Adversarial Attacks? Linking Adversarial and Perturbation Robustness20 Jan 2026
- 2024Attacking Bayes: On the Adversarial Robustness of Bayesian Neural Networks27 Apr 2024
- 2023A Primer on Bayesian Neural Networks: Review and Debates28 Sep 2023
- 2023Adversarial Attacks Against Uncertainty Quantification19 Sep 2023
- 2023A reading survey on adversarial machine learning: Adversarial attacks and their understanding7 Aug 2023
- 2023Dynamic ensemble selection based on Deep Neural Network Uncertainty Estimation for Adversarial Robustness1 Aug 2023
- 2022On the Robustness of Bayesian Neural Networks to Adversarial Attacks13 Jul 2022
- 2022Adversarial Example Detection in Deployed Tree Ensembles27 Jun 2022
- 2021Exploiting Vulnerabilities in Deep Neural Networks: Adversarial and Fault-Injection Attacks5 May 2021
- 2021Adversarial Robustness Guarantees for Gaussian Processes7 Apr 2021
- 2021LiBRe: A Practical Bayesian Approach to Adversarial Detection27 Mar 2021
12 newest of 14 All 14 (JSON)