Pith. sign in

REVIEW 1 cited by

Adversarial Training Using Feedback Loops

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 2308.11881 v2 pith:ZW3WX444 submitted 2023-08-23 cs.LG cs.CR

classification cs.LGcs.CR
keywords adversarialfeedbackneuralcontroldnnsnetworktrainingapproach
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Deep neural networks (DNN) have found wide applicability in numerous fields due to their ability to accurately learn very complex input-output relations. Despite their accuracy and extensive use, DNNs are highly susceptible to adversarial attacks due to limited generalizability. For future progress in the field, it is essential to build DNNs that are robust to any kind of perturbations to the data points. In the past, many techniques have been proposed to robustify DNNs using first-order derivative information of the network. This paper proposes a new robustification approach based on control theory. A neural network architecture that incorporates feedback control, named Feedback Neural Networks, is proposed. The controller is itself a neural network, which is trained using regular and adversarial data such as to stabilize the system outputs. The novel adversarial training approach based on the feedback control architecture is called Feedback Looped Adversarial Training (FLAT). Numerical results on standard test problems empirically show that our FLAT method is more effective than the state-of-the-art to guard against adversarial attacks.

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. Transforming Chatbot Text: A Sequence-to-Sequence Approach

    cs.CL 2025-06 conditional novelty 4.0 of 10

    Fine-tuned T5-small and BART can lower the accuracy of GPT-text classifiers, but retraining the classifiers on the transformed text restores detection accuracy.

Pith tools