Ares: A framework for quantifying the resilience of deep neural networks
The DOI matches its Crossref record; 8 of the 8 references it cites were found in a registry or an index.
Abstract
As the use of deep neural networks continues to grow, so does the fraction of compute cycles devoted to their execution. This has led the CAD and architecture communities to devote considerable attention to building DNN hardware. Despite these efforts, the fault tolerance of DNNs has generally been overlooked. This paper is the first to conduct a large-scale, empirical study of DNN resilience. Motivated by the inherent algorithmic resilience of DNNs, we are interested in understanding the relationship between fault rate and model accuracy. To do so, we present Ares: a light-weight, DNN-specific fault injection framework validated within 12% of real hardware. We find that DNN fault tolerance varies by orders of magnitude with respect to model, layer type, and structure.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“In prior work, Ares by Reagen et al. [40] offers a fault resilience evaluation platform for DNN models based on PyTorch.”
From Fine-Grained Fault Sensitivity Analysis of Vision Transformers Under Soft Errors (2025) · cites this paper as [40]
In the citing paper
“It differs from prior neuron-wise fault injection frameworks [18] [19] [51] that fail to cover the non-linear functions”
From Soft Error Reliability Analysis of Vision Transformers (2023) · cites this paper as [18]
Citations
Cites
Theano: A CPU and GPU Math Compiler in Python
Bergstra, J., Breuleux, O., Bastien, F., Lamblin, P., Pascanu, R., Desjardins, G., Turian, J., Warde-Farley, D., & Bengio, Y. (2010) · Proceedings of the Python in Science Conference · doi:10.25080/majora-92bf1922-003 · Cited by 1,052
Understanding error propagation in deep learning neural network (DNN) accelerators and applications
Li, G., Hari, S. K. S., Sullivan, M., Tsai, T., Pattabiraman, K., Emer, J., & Keckler, S. W. (2017) · Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis · doi:10.1145/3126908.3126964 · Cited by 492
Reliability Issues in Computing System Design
Randell, B., Lee, P., & Treleaven, P. C. (1978) · ACM Computing Surveys · doi:10.1145/356725.356729 · Cited by 383
Minerva: Enabling Low-Power, Highly-Accurate Deep Neural Network Accelerators
Reagen, B., Whatmough, P., Adolf, R., Rama, S., Lee, H., Lee, S. K., Hernandez-Lobato, J. M., Wei, G.-Y., & Brooks, D. (2016) · 2016 ACM/IEEE 43rd Annual International Symposium on Computer Architecture (ISCA) · doi:10.1109/isca.2016.32 · Cited by 246
Self-citationSASSIFI: An architecture-level fault injection tool for GPU application resilience evaluation
Hari, S. K. S., Tsai, T., Stephenson, M., Keckler, S. W., & Emer, J. (2017) · 2017 IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS) · doi:10.1109/ispass.2017.7975296 · Cited by 181
A defect-tolerant accelerator for emerging high-performance applications
Temam, O. (2012) · ACM SIGARCH Computer Architecture News · doi:10.1145/2366231.2337200 · Cited by 139
Paul, N., Lee, S. K., Lee, H., Rama, S., David, B., & Wei, G.-Y. (2017) · IEEE Conference Proceedings · Cited by 77
Self-citationRobustness in Multilayer Perceptrons
Kerlirzin, P., & VALLET, F. (1993) · Neural Computation · doi:10.1162/neco.1993.5.3.473 · Cited by 54
Research works printed but not linked: 5
- 2018, Keras The Python deep learning library
- 2018, TensorFlow «TensorFlow is an Open Source Software Library for Machine Intelligence
- goodfellow, 2016, Deep Learning
- cun, 1990, Optimal brain damage, NIPS
- 2017, Solid State Drive (SSD) Requirements and Endurance Test Method
Cited by
Photonic Multiply-Accumulate Operations for Neural Networks
Nahmias, M. A., de Lima, T. F., Tait, A. N., Peng, H.-T., Shastri, B. J., & Prucnal, P. R. (2020) · IEEE Journal of Selected Topics in Quantum Electronics · doi:10.1109/jstqe.2019.2941485 · Cited by 301
A survey on modeling and improving reliability of DNN algorithms and accelerators
Mittal, S. (2020) · Journal of Systems Architecture · doi:10.1016/j.sysarc.2019.101689 · Cited by 175
Selective Hardening for Neural Networks in FPGAs
Libano, F., Wilson, B., Anderson, J., Wirthlin, M., Cazzaniga, C., Frost, C. D., & Rech, P. (2018) · IEEE Transactions on Nuclear Science · doi:10.1109/tns.2018.2884460 · Cited by 164
EdgeBERT: Sentence-Level Energy Optimizations for Latency-Aware Multi-Task NLP Inference
Tambe, T., Hooper, C., Pentecost, L., Jia, T., Yang, E.-Y., Donato, M., Sanh, V., Whatmough, P., Rush, A. M., Brooks, D., et al. (2021) · MICRO-54: 54th Annual IEEE/ACM International Symposium on Microarchitecture · doi:10.1145/3466752.3480095 · Cited by 120
Self-citationChakraborty, I., Ali, M., Ankit, A., Jain, S., Roy, S., Sridharan, S., Agrawal, A., Raghunathan, A., & Roy, K. (2020) · Proceedings of the IEEE · doi:10.1109/jproc.2020.3003007 · Cited by 140
Metadata
- Authors
- Reagen, B., Gupta, U., Pentecost, L., Whatmough, P., Lee, S. K., Mulholland, N., Brooks, D., & Wei, G.-Y.
- Affiliations
- Harvard University (US)
- ORCID
- Venue
- 2018 55th ACM/ESDA/IEEE Design Automation Conference (DAC)
- Publisher
- IEEE
- Published
- 2018-06
- Pages
- 1-6
- ISSN
- 0738-100X (ISSN-L)
- OpenAlex
- W4252174618
- Cited by
- 189
- References
- 8
- Citations by year
- 2026: 16 · 2025: 31 · 2024: 27 · 2023: 35 · 2022: 26 · 2021: 18 · 2020: 15 · 2019: 17 · 2018: 4
- FWCI
- 11.16
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- ACM/IEEE Design Automation Conference (DAC) (publishedVersion)
- Funders
- Semiconductor Research Corporation
- Defense Advanced Research Projects Agency
- Topics
- Physical Sciences › Computer Science › Computer Networks and Communications › Distributed systems and fault tolerance
- Physical Sciences › Engineering › Electrical and Electronic Engineering › Radiation Effects in Electronics
- Physical Sciences › Computer Science › Hardware and Architecture › VLSI and Analog Circuit Testing
- Keywords
- deep neural network, fault tolerance, fault injection, model accuracy, fault rate, neural network layers
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.