Papers › The Limitations of Deep Learning in Adversarial Settings

The Limitations of Deep Learning in Adversarial Settings

24 Nov 2015arXiv:1511.07528archive 2025-07-28

Nicolas Papernot, Patrick McDaniel, Somesh Jha, Matt Fredrikson, Z. Berkay Celik, Ananthram Swami

Deep learning takes advantage of large datasets and computationally efficient training algorithms to outperform other approaches at various machine learning tasks. However, imperfections in the training phase of deep neural networks make them vulnerable to adversarial samples: inputs crafted by adversaries with the intent of causing deep neural networks to misclassify. In this work, we formalize the space of adversaries against deep neural networks (DNNs) and introduce a novel class of algorithms to craft adversarial samples based on a precise understanding of the mapping between inputs and outputs of DNNs. In an application to computer vision, we show that our algorithms can reliably produce samples correctly classified by human subjects but misclassified in specific targets by a DNN with a 97% adversarial success rate while only modifying on average 4.02% of the input features per sample. We then evaluate the vulnerability of different sample classes to adversarial perturbations by defining a hardness measure. Finally, we describe preliminary work outlining defenses against adversarial samples by defining a predictive measure of distance between a benign input and a target classification.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

AngusG/cleverhans-attacking-bnns mentioned on GitHubtfMIT report
HowToMakeABomb101/Hot2MakeAB0mbSite mentioned on GitHubtfMIT report
cleverhans-lab/cleverhans mentioned on GitHubtfMIT report
elites2k19/prism-attack mentioned on GitHubtfMIT report
formal-verification-research/NJSMA mentioned on GitHubtfMIT report
iirishikaii/cleverhans mentioned on GitHubtfMIT report
johnsonkee/graduate_design mentioned on GitHubtfMIT report
openai/cleverhans mentioned on GitHubtf report
shijiel2/cleverhans mentioned on GitHubtf report
tensorflow/cleverhans mentioned on GitHubtfMIT report
yaq007/cleverhans mentioned on GitHubtfMIT report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Adversarial AttackAdversarial DefenseDeep Learning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections