Pith. sign in

REVIEW

Decoder-free Robustness Disentanglement without (Additional) Supervision

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 2007.01356 v1 pith:G5N3KEQK submitted 2020-07-02 stat.ML cs.CVcs.LGcs.NE

classification stat.MLcs.CVcs.LGcs.NE
keywords adversarialfeaturesnon-robustrobustaccuracyadditionaldisentanglementlearning
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Adversarial Training (AT) is proposed to alleviate the adversarial vulnerability of machine learning models by extracting only robust features from the input, which, however, inevitably leads to severe accuracy reduction as it discards the non-robust yet useful features. This motivates us to preserve both robust and non-robust features and separate them with disentangled representation learning. Our proposed Adversarial Asymmetric Training (AAT) algorithm can reliably disentangle robust and non-robust representations without additional supervision on robustness. Empirical results show our method does not only successfully preserve accuracy by combining two representations, but also achieve much better disentanglement than previous work.

Discussion (0). Sign in to comment.

Pith tools