AI Paper Atlas

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

Robust Fine-Tuning from Non-Robust Pretrained Models: Mitigating Suboptimal Transfer With Epsilon-Scheduling

Jonas Ngnawe, Maxime Heuillet, Sabyasachi Sahoo, Yann Pequignot, Ola Ahmad, Audrey Durand, Frederic Precioso, Christian Gagné

ICLR 2026 · Adversarial robustness and security › Certified and empirical robustness · approach: Theory of adversarial risk · 2 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 epsilon-scheduling (zero-epsilon warmup then linear ramp) to robust fine-tuningRFT-fix, SWIN · Aircraft (eps=4/255)clean accuracy: 7.70 -> 73.80Improved
add epsilon-scheduling to robust fine-tuningRFT-fix, ClipCNX · Cars (eps=8/255)clean accuracy: 1.30 -> 90.00Improved
add epsilon-schedulingRFT-fix, six non-robust backbones · 5 datasets avg (eps=8/255)expected adversarial accuracy: 10.12 -> 34.38 (ViT)Improved
add epsilon-schedulingRFT-fix, six backbones · 30 configurations (eps=4/255)adversarial accuracy: fix better adversarial accuracy in 9 of 30Mixed
add epsilon-schedulingRFT-fix, six backbones · 30 configurations (eps=8/255)adversarial accuracy: scheduler better in 28 of 30Improved
add epsilon-scheduling to robust pretrained backboneRFT-fix, RobSWIN · Cars (eps=8/255)expected adversarial accuracy: 50.62 -> 63.88Improved
add epsilon-scheduling to robust pretrained backboneRFT-fix, RobCNX · Aircraft (eps=4/255)adversarial accuracy: 62.00 -> 49.70Hurt
add zero-epsilon warmup phase T1=12 (vs T1=0) with T2=30 (ablation)Linear warmup, SWIN · Cars (eps=4/255)expected adversarial accuracy: 63.41 -> 67.09Improved
use gradual ramp (T2=37) instead of abrupt switch (T1=T2=12) (ablation)Delayed switch, SWIN · Cars (eps=4/255)clean accuracy: 1.90 -> 84.70Improved
lengthen ramp from T2=37 to T2=50 at T1=12 (ablation)Epsilon-Scheduling, SWIN · Cars (eps=4/255)adversarial accuracy: 43.20 -> 35.80Hurt
use scheduled epsilon instead of uniform random epsilon (ablation)Uniform random epsilon, SWIN · Cars (eps=8/255)expected adversarial accuracy: 30.16 -> 53.57Improved
use scheduled epsilon instead of uniform random epsilon (ablation)Uniform random epsilon, ClipCNX · Aircraft (eps=4/255)expected adversarial accuracy: 5.78 -> 67.88Improved

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