REVIEW 2 cited by
Adversary Detection in Neural Networks via Persistent Homology
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Signed reviews
read the original abstract
We outline a detection method for adversarial inputs to deep neural networks. By viewing neural network computations as graphs upon which information flows from input space to out- put distribution, we compare the differences in graphs induced by different inputs. Specifically, by applying persistent homology to these induced graphs, we observe that the structure of the most persistent subgraphs which generate the first homology group differ between adversarial and unperturbed inputs. Based on this observation, we build a detection algorithm that depends only on the topological information extracted during training. We test our algorithm on MNIST and achieve 98% detection adversary accuracy with F1-score 0.98.
Forward citations
Cited by 2 Pith papers
-
How fine a change can moments see? A scale law for detecting distribution shift, with a kernel calibration rule
Moment-based detection of an epsilon-scale, mass-f distribution change requires polynomial degree at least log(1/f)/(2 epsilon), which yields a bandwidth rule for kernel shift tests.
-
Topology of Out-of-Distribution Examples in Deep Neural Networks
Out-of-distribution images show longer average H0 persistence lifetimes in a ResNet18 embedding layer than in-distribution training and test images.
Discussion (0). Continue with ORCID to comment.