CoChat

Poisoning attacks to compromise face templates

Open access
Biggio, Battista, Didaci, Luca, Fumera, Giorgio, Roli, Fabio · 2013 · 2013 International Conference on Biometrics (ICB)
Cited by 76

The DOI matches its Crossref record; 2 of the 2 references it cites were found in a registry or an index.

Abstract

Adaptive biometric systems update clients' templates during operation to account for natural changes over time (e.g., aging of biometric templates). Recently, it has been shown that this update can be exploited by an attacker to compromise the clients' templates: by presenting a proper sequence of fake biometric traits to the sensor, the attacker may eventually impersonate the targeted clients without any fake trait, and even force the system to deny access to them. This attack has however been shown only for PCA-based face verification, with one template per client, under worstcase assumptions about the attacker's knowledge of the sys-tem. In this paper, we show that it can be successful even in the case of multiple templates per client, for different matchers, and under more realistic scenarios, and validate it by experiments to highlight its practical relevance.

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

Crossref · 10.1109/icb.2013.6613006

Cites

2 of 2 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

  • Adversarial machine learning

    Huang, 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×

    “According to a recent taxonomy of potential attacks against machine learning algorithms [5], the attacker’s goal can be defined by the desired security violation, which may be an integrity, availability, or privacy violation.”
    Background
  • Casting out Demons: Sanitizing Training Data for Anomaly Sensors

    Cretu, G. F., Stavrou, A., Locasto, M. E., Stolfo, S. J., & Keromytis, A. D. (2008) · 2008 IEEE Symposium on Security and Privacy (sp 2008) · doi:10.1109/sp.2008.11 · Cited by 226 · cited 2×

    “3, one may adopt fusion rules that produce similar effects to data sanitization [2] (like the mean rule), namely, that prevent some of the client’s templates to be shifted too far from the rest of the gallery.”
    Background

Show all 2 references

Cited by

See all 76

Metadata

Authors
Biggio, B., Didaci, L., Fumera, G., & Roli, F.
Venue
2013 International Conference on Biometrics (ICB)
Publisher
IEEE
Published
2013-06
Pages
1-7
OpenAlex
W2088454850
Cited by
76
References
2
FWCI
2.50
Type
conference paper
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: Poisoning attacks to compromise face templates. https://app.cochat.ai/papers/10.1109/icb.2013.6613006
The paper
Biggio, B., Didaci, L., Fumera, G., & Roli, F. (2013). Poisoning attacks to compromise face templates. 2013 International Conference on Biometrics (ICB). https://doi.org/10.1109/icb.2013.6613006

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.