Skip to content
conftrace_

model certification

3 papers

Explore in graph

Co-occurring keywords · papers mentioning both

adversarial attack (2) adversarial robustness (2) reward certification (1) policy smoothing (1) convex optimisation (1) safety certification (1) safe certification (1) statistical guarantee (1) model poisoning (1) cumulative reward (1)

Papers

PROSAC: Provably Safe Certification for Machine Learning Models under Adversarial Attacks AAAI 2025 Reward Certification for Policy Smoothed Reinforcement Learning AAAI 2024 CRFL: Certifiably Robust Federated Learning against Backdoor Attacks ICML 2021