Pith. sign in

REVIEW 1 cited by

Detecting AI Trojans Using Meta Neural Analysis

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 1910.03137 v4 pith:AGNZFCHB submitted 2019-10-08 cs.AI cs.CRcs.LG

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

In machine learning Trojan attacks, an adversary trains a corrupted model that obtains good performance on normal data but behaves maliciously on data samples with certain trigger patterns. Several approaches have been proposed to detect such attacks, but they make undesirable assumptions about the attack strategies or require direct access to the trained models, which restricts their utility in practice. This paper addresses these challenges by introducing a Meta Neural Trojan Detection (MNTD) pipeline that does not make assumptions on the attack strategies and only needs black-box access to models. The strategy is to train a meta-classifier that predicts whether a given target model is Trojaned. To train the meta-model without knowledge of the attack strategy, we introduce a technique called jumbo learning that samples a set of Trojaned models following a general distribution. We then dynamically optimize a query set together with the meta-classifier to distinguish between Trojaned and benign models. We evaluate MNTD with experiments on vision, speech, tabular data and natural language text datasets, and against different Trojan attacks such as data poisoning attack, model manipulation attack, and latent attack. We show that MNTD achieves 97% detection AUC score and significantly outperforms existing detection approaches. In addition, MNTD generalizes well and achieves high detection performance against unforeseen attacks. We also propose a robust MNTD pipeline which achieves 90% detection AUC even when the attacker aims to evade the detection with full knowledge of the system.

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. Comprehensive Evaluation of Cloaking Backdoor Attacks on Object Detector in Real-World

    cs.CR 2025-01 conditional novelty 6.0 of 10

    A blue bear-logo T-shirt used as a data-poisoning trigger can erase people from YOLO, CenterNet, and even Faster R-CNN detectors in real video with near-100% success and no drop in clean accuracy.

Pith tools