CoChat

Terminal brain damage: exposing the graceless degradation in deep neural networks under hardware fault attacks

Open access
Sanghyun Hong, Pietro Frigo, Yiğitcan Kaya, Cristiano Giuffrida, Tudor Dumitraş · 2019 · arXiv (Cornell University)
DOI 10.5555/3361338.3361373
PreprintCited by 43

The DOI matches its OpenAlex record; 12 of the 12 references it cites were found in a registry or an index.

Abstract

Deep neural networks (DNNs) have been shown to tolerate brain damage: cumulative changes to the network's parameters (e.g., pruning, numerical perturbations) typically result in a graceful degradation of classification accuracy. However, the limits of this natural resilience are not well understood in the presence of small adversarial changes to the DNN parameters' underlying memory representation, such as bit-flips that may be induced by hardware fault attacks. We study the effects of bitwise corruptions on 19 DNN models--six architectures on three image classification tasks--and we show that most models have at least one parameter that, after a specific bit-flip in their bitwise representation, causes an accuracy loss of over 90%. For large models, we employ simple heuristics to identify the parameters likely to be vulnerable and estimate that 40-50% of the parameters in a model might lead to an accuracy drop greater than 10% when individually subjected to such single-bit perturbations. To demonstrate how an adversary could take advantage of this vulnerability, we study the impact of an exemplary hardware fault attack, Rowhammer, on DNNs. Specifically, we show that a Rowhammer-enabled attacker co-located in the same physical machine can inflict significant accuracy drops (up to 99%) even with single bitflip corruptions and no knowledge of the model. Our results expose the limits of DNNs' resilience against parameter perturbations induced by real-world fault attacks. We conclude by discussing possible mitigations and future research directions towards fault attack-resilient DNNs.

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.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

OpenAlex · 10.5555/3361338.3361373

Cites

12 of 12 references verified0 citation errors · 0 not checkable

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.

A few free checks a day · papers already verified open instantly · results are public

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

Show all 12 references

Cited by

See all 43

Metadata

Authors
Hong, S., Frigo, P., Kaya, Y., Giuffrida, C., & Dumitraş, T.
Venue
arXiv (Cornell University)
Publisher
Cornell University
Published
2019-08-14
Pages
497-514
ISSN
2331-8422 (ISSN-L)
DOI
10.5555/3361338.3361373
OpenAlex
W2964923388
Cited by
43
References
12
Type
posted content
Language
en
Open access
green

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

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: Terminal brain damage: exposing the graceless degradation in deep neural networks under hardware fault attacks. https://app.cochat.ai/papers/10.5555/3361338.3361373
The paper
Hong, S., Frigo, P., Kaya, Y., Giuffrida, C., & Dumitraş, T. (2019). Terminal brain damage: exposing the graceless degradation in deep neural networks under hardware fault attacks. arXiv (Cornell University). https://doi.org/10.5555/3361338.3361373

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.