Skip to content
conftrace_

verified accuracy

3 papers

Explore in graph

Co-occurring keywords · papers mentioning both

adversarial robustness (3) interval bound propagation (2) abstain class (1) synonym replacement (1) provable robustness (1) symbol substitution (1) character flip perturbation (1) certified defense (1) neural network verification (1) adversarial attack (1)

Papers

Improving Adversarial Robustness via Joint Classification and Multiple Explicit Detection Classes AISTATS 2023 Achieving Verified Robustness to Symbol Substitutions via Interval Bound Propagation EMNLP 2019 Scalable Verified Training for Provably Robust Image Classification ICCV 2019