Analyzing the Robustness of Open-World Machine Learning
Open accessThe DOI matches its Crossref record; 22 of the 22 references it cites were found in a registry or an index.
Abstract
When deploying machine learning models in real-world applications, an open-world learning framework is needed to deal with both normal in-distribution inputs and undesired out-of-distribution (OOD) inputs. Open-world learning frameworks include OOD detectors that aim to discard input examples which are not from the same distribution as the training data of machine learning classifiers. However, our understanding of current OOD detectors is limited to the setting of benign OOD data, and an open question is whether they are robust in the presence of adversaries. In this paper, we present the first analysis of the robustness of open-world learning frameworks in the presence of adversaries by introducing and designing øodAdvExamples. Our experimental results show that current OOD detectors can be easily evaded by slightly perturbing benign OOD inputs, revealing a severe limitation of current open-world learning frameworks. Furthermore, we find that øodAdvExamples also pose a strong threat to adversarial training based defense methods in spite of their effectiveness against in-distribution adversarial attacks. To counteract these threats and ensure the trustworthy detection of OOD inputs, we outline a preliminary design for a robust open-world machine learning framework.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155
LeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126
ImageNet: A large-scale hierarchical image database
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206848 · Cited by 65,333
Towards Evaluating the Robustness of Neural Networks
Carlini, N., & Wagner, D. (2017) · 2017 IEEE Symposium on Security and Privacy (SP) · doi:10.1109/sp.2017.49 · Cited by 8,859
Zagoruyko, S., & Komodakis, N. (2016) · Procedings of the British Machine Vision Conference 2016 · doi:10.5244/c.30.87 · Cited by 7,244
Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
Xiao, H., Rasul, K., & Vollgraf, R. (2017) · arXiv · doi:10.48550/arxiv.1708.07747 · Cited by 6,108
Striving for Simplicity: The All Convolutional Net
Springenberg, J. T., Dosovitskiy, A., Brox, T., & Riedmiller, M. (2014) · arXiv · doi:10.48550/arxiv.1412.6806 · Cited by 3,447
Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Images
Nguyen, A., Yosinski, J., & Clune, J. (2014) · arXiv · doi:10.48550/arxiv.1412.1897 · Cited by 3,258
Deep neural networks are easily fooled: High confidence predictions for unrecognizable images
Nguyen, A., Yosinski, J., & Clune, J. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298640 · Cited by 3,258
End to End Learning for Self-Driving Cars
Bojarski, M., Del Testa, D., Dworakowski, D., Firner, B., Flepp, B., Goyal, P., Jackel, L. D., Monfort, M., Muller, U., Zhang, J., et al. (2016) · arXiv · doi:10.48550/arxiv.1604.07316 · Cited by 3,198
A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks
Lee, K., Lee, K., Lee, H., & Shin, J. (2018) · arXiv · doi:10.48550/arxiv.1807.03888 · Cited by 2,450
Torralba, A., & Efros, A. A. (2011) · CVPR 2011 · doi:10.1109/cvpr.2011.5995347 · Cited by 2,440
Ensemble Adversarial Training: Attacks and Defenses
Tramèr, F., Kurakin, A., Papernot, N., Goodfellow, I., Boneh, D., & McDaniel, P. (2017) · arXiv · doi:10.48550/arxiv.1705.07204 · Cited by 2,176 · cited 3×
“Robust training is one of the most effective methods to achieve robustness against adversarial attacks on deep neural networks [26, 38, 46, 52, 64].”
BackgroundMethodObfuscated gradients give a false sense of security: Circumventing defenses to adversarial examples
Athalye, A., Carlini, N., & Wagner, D. (2018) · arXiv · doi:10.48550/arxiv.1802.00420 · Cited by 2,172 · cited 4×
“While in the former the adversary has complete access to the classifier, including employed defenses, dataset, and hyperparameters, the latter threat model only allows access to the output probability distribution д (·) for any input x ∈ X [3, 11, 26, 62].”
BackgroundMethodInfluentialDeep Learning for Anomaly Detection: A Survey
Chalapathy, R., & Chawla, S. (2019) · arXiv · doi:10.48550/arxiv.1901.03407 · Cited by 1,240 · cited 1×
“The importance of this learning model is highlighted by the fact that a number of security and safety-critical applications such as biometric authentication, intrusion detection, autonomous driving, medical diagnosis are natural settings for the use of open-world machine learning [13, 27, 45, 53].”
BackgroundHuang, L., Joseph, A. D., Nelson, B., Rubinstein, B. I. P., & Tygar, J. D. (2011) · Proceedings of the 4th ACM workshop on Security and artificial intelligence · doi:10.1145/2046684.2046692 · Cited by 1,194 · cited 1×
“[34], OOD adversarial examples are a form of exploratory integrity attacks with the intent of targeted misclassification of input data.”
BackgroundFeature denoising for improving adversarial robustness
Xie, C., Wu, Y., Maaten, L. V. D., Yuille, A. L., & He, K. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00059 · Cited by 940
Deep Anomaly Detection with Outlier Exposure
Hendrycks, D., Mazeika, M., & Dietterich, T. (2018) · arXiv · doi:10.48550/arxiv.1812.04606 · Cited by 932
Evasion Attacks against Machine Learning at Test Time
Biggio, B., Corona, I., Maiorca, D., Nelson, B., Šrndić, N., Laskov, P., Giacinto, G., & Roli, F. (2013) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-40994-3_25 · Cited by 890 · cited 2×
“In this paper, we thoroughly evaluate the performance of open-world machine learning models against such maliciously-perturbed OOD inputs, which we refer to as OOD adversarial examples , motivated by the line of research on adversarial attacks against neural networks [8, 11, 62].”
BackgroundMethodTowards Open World Recognition
Bendale, A., & Boult, T. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298799 · Cited by 529 · cited 2×
“…input data, an important line of work has developed the open-world learning framework that checks if the inputs are within the same distribution as training data (in-distribution examples), or if they come from a different distribution referred to as out-of-distribution (OOD) examples [5, 6].”
BackgroundSelective Classification for Deep Neural Networks
Geifman, Y., & El-Yaniv, R. (2017) · arXiv · doi:10.48550/arxiv.1705.08500 · Cited by 220
Cited by
RobustBench: a standardized adversarial robustness benchmark
Croce, F., Andriushchenko, M., Sehwag, V., Debenedetti, E., Flammarion, N., Chiang, M., Mittal, P., & Hein, M. (2020) · arXiv · doi:10.48550/arxiv.2010.09670 · Cited by 284
“An emerging line of research aims at 292 developing OOD detection methods in conjunction with adversarial robustness [52, 109, 7].”
BackgroundSelf-citationHanneman, K., Playford, D., Dey, D., van Assen, M., Mastrodicasa, D., Cook, T. S., Gichoya, J. W., Williamson, E. E., Rubin, G. D., & on behalf of the American Heart Association Council on Cardiovascular Radiology and Intervention; and Council on Lifelong Congenital Heart Disease and Heart Health in the Young (2024) · Circulation · doi:10.1161/cir.0000000000001202 · Cited by 72
Non-Determinism of “Deterministic” LLM System Settings in Hosted Environments
Atıl, B., Aykent, S., Chittams, A., Fu, L., Passonneau, R. J., Radcliffe, E., Rajagopal, G. R., Sloan, A., Tudrej, T., Ture, F., et al. (2025) · Proceedings of the 5th Workshop on Evaluation and Comparison of NLP Systems · doi:10.18653/v1/2025.eval4nlp-1.12 · Cited by 36
Towards Detection of AI-Generated Texts and Misinformation
Najee-Ullah, A., Landeros, L., Balytskyi, Y., & Chang, S.-Y. (2022) · Lecture Notes in Computer Science · doi:10.1007/978-3-031-10183-0_10 · Cited by 18
Understanding the Challenges When 3D Semantic Segmentation Faces Class Imbalanced and OOD Data
Pan, Y., Xie, F., & Zhao, H. (2023) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2023.3256442 · Cited by 17
“cations need to address the open-world problem [42], which requires the models to deal with both the seen (ID) and unseen (OOD) objects in the training datasets.”
Background
Metadata
- Authors
- Sehwag, V., Bhagoji, A. N., Song, L., Sitawarin, C., Cullina, D., Chiang, M., & Mittal, P.
- Venue
- Proceedings of the 12th ACM Workshop on Artificial Intelligence and Security
- Publisher
- ACM
- Published
- 2019-11-11
- Pages
- 105-116
- OpenAlex
- W2983041926
- Cited by
- 69
- References
- 22
- FWCI
- 3.41
- Type
- conference paper
- Language
- en
- Open access
- hybrid
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.