AI Paper Atlas

Research map / Adversarial robustness and security / Certified and empirical robustness

Adversarial Robust Memory-Based Continual Learner

Xiaoyue Mi, Fan Tang, Zonghan Yang, Danding Wang, Juan Cao, Peng Li, Yang Liu

ICCV 2025 · Adversarial robustness and security › Certified and empirical robustness · approach: Adversarial training refinements · 7 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add anti-forgettable logit calibration (AFLC) (ablation)ER+TRADES · Split-CIFAR10 (buffer 200, class-incremental)clean forgetting: 77.25 -> 21.76Improved
add AFLC (ablation)ER+TRADES · Split-CIFAR10 (buffer 200, class-incremental)clean FAA: 22.42 -> 37.88Improved
add AFLC (ablation)ER+TRADES · Split-CIFAR10 (buffer 200, task-incremental)clean forgetting: 8.10 -> 10.86Hurt
add robustness-aware experience replay (RAER) on top of AFLC (ablation)ER+TRADES+AFLC · Split-CIFAR10 (buffer 200, class-incremental)adversarial FAA: 18.58 -> 19.81Improved
add RAER on top of AFLC (ablation)ER+TRADES+AFLC · Split-CIFAR10 (buffer 200, task-incremental)adversarial FAA: 53.64 -> 55.71Improved
add RAER on top of AFLC (ablation)ER+TRADES+AFLC · Split-CIFAR10 (buffer 200, class-incremental)adversarial forgetting: 21.77 -> 9.61Improved
add future prior adjustment (FP) (ablation)ER+TRADES+AFLC+RAER · Split-CIFAR10 (buffer 200, class-incremental)clean FAA: 37.45 -> 43.34Improved
add future prior adjustment (FP) (ablation)ER+TRADES+AFLC+RAER · Split-CIFAR10 (buffer 200, class-incremental)clean forgetting: 10.29 -> 33.40Hurt
apply RAER data selection threshold rho=5 only (without AFLC) (ablation)ER+TRADES · Split-CIFAR10 (buffer 200, class-incremental)clean FAA: 22.42 -> 18.21Hurt
apply RAER data selection threshold rho=10 only (without AFLC) (ablation)ER+TRADES · Split-CIFAR10 (buffer 200, task-incremental)adversarial FAA: 51.33 -> 59.88Improved
increase calibration alpha from 3.5 to 7.0 (ablation)AFLC · Split-CIFAR10 (buffer 200, class-incremental)adversarial FAA: 18.58 -> 13.89Hurt
add our method (AFLC + RAER)ER+TRADES · Split-CIFAR10 (buffer 200, task-incremental)adversarial FAA (PGD-20): 51.33 -> 59.41Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy