AI Paper Atlas

Research map / Large language models / Instruction and fine-tuning

Enhancing Fine-Tuning Based Backdoor Defense with Sharpness-Aware Minimization

Mingli Zhu, Shaokui Wei, Li Shen, Yanbo Fan, Baoyuan Wu

ICCV 2023 · Large language models › Instruction and fine-tuning · approach: Safety alignment after fine-tuning · 73 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
replace vanilla fine-tuning with sharpness-aware fine-tuning (FT-SAM)backdoored PreAct-ResNet18 defense · CIFAR-10 5% benign, average over 10 attacksASR (%): 38.81 -> 2.47Improved
replace vanilla fine-tuning with FT-SAMbackdoored PreAct-ResNet18 defense · Tiny ImageNet 5% benign, average over attacksASR (%): 41.76 -> 1.16Improved
replace FT with FT-SAM under Blended attack with 5% benign dataCIFAR-10 PreAct-ResNet18 · CIFAR-10 Blended 10% poisonASR (%): 82.22 -> 4.91Improved
reduce benign data from 10% to 1% for FT-SAM (ablation)FT-SAM · CIFAR-10 PreAct-ResNet18DERNo clear effect
replace FT with FT-SAM in the FP pruning pipeline (ablation)Fine-pruning · CIFAR-10 CLA attackASR (%): 78.72 -> 33.76Improved
replace FT with FT-SAM after ANP masking (ablation)ANP · CIFAR-10 Blended attackASR (%): 42.28 -> 2.57Improved
vary perturbation bound rho (smaller values) (ablation)FT-SAM · CIFAR-10 complex attacksASR / DERNo clear effect

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