Papers › Semidefinite relaxations for certifying robustness to adversarial examples

Semidefinite relaxations for certifying robustness to adversarial examples

2 Nov 2018NeurIPS 2018 12arXiv:1811.01057archive 2025-07-28

Aditi Raghunathan, Jacob Steinhardt, Percy Liang

Despite their impressive performance on diverse tasks, neural networks fail catastrophically in the presence of adversarial inputs---imperceptibly but adversarially perturbed versions of natural inputs. We have witnessed an arms race between defenders who attempt to train robust networks and attackers who try to construct adversarial examples. One promise of ending the arms race is developing certified defenses, ones which are provably robust against all attackers in some family. These certified defenses are based on convex relaxations which construct an upper bound on the worst case loss over all attackers in the family. Previous relaxations are loose on networks that are not trained against the respective relaxation. In this paper, we propose a new semidefinite relaxation for certifying robustness that applies to arbitrary ReLU networks. We show that our proposed relaxation is tighter than previous relaxations and produces meaningful robustness guarantees on three different "foreign networks" whose training objectives are agnostic to our proposed relaxation.

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

GuanZihan/verification mentioned on GitHubtf report
TongCHEN779/MultiMomOpt mentioned on GitHubGPL-3.0 report
soc-ucsd/verification mentioned on GitHubtf report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections