Pith. sign in

REVIEW 1 cited by

Neural Architectural Backdoors

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

arxiv 2210.12179 v2 pith:O2HH4YVA submitted 2022-10-21 cs.CR cs.LG

classification cs.CRcs.LG
keywords evasneuralattackattacksbackdoorsdatamodelparameters
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

This paper asks the intriguing question: is it possible to exploit neural architecture search (NAS) as a new attack vector to launch previously improbable attacks? Specifically, we present EVAS, a new attack that leverages NAS to find neural architectures with inherent backdoors and exploits such vulnerability using input-aware triggers. Compared with existing attacks, EVAS demonstrates many interesting properties: (i) it does not require polluting training data or perturbing model parameters; (ii) it is agnostic to downstream fine-tuning or even re-training from scratch; (iii) it naturally evades defenses that rely on inspecting model parameters or training data. With extensive evaluation on benchmark datasets, we show that EVAS features high evasiveness, transferability, and robustness, thereby expanding the adversary's design spectrum. We further characterize the mechanisms underlying EVAS, which are possibly explainable by architecture-level ``shortcuts'' that recognize trigger patterns. This work raises concerns about the current practice of NAS and points to potential directions to develop effective countermeasures.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Architectural Backdoors in Deep Learning: A Survey of Vulnerabilities, Detection, and Defense

    cs.CR 2025-07 conditional novelty 4.0 of 10

    Architectural backdoors are a persistent class of neural-network backdoors that survive clean retraining, and current detection tools and benchmarks are not ready for them.

Pith tools