AI Paper Atlas

Research map / Adversarial robustness and security / Black-box and transfer attacks

Label-Only Model Inversion Attacks via Knowledge Transfer

Ngoc-Bao Nguyen, Keshigeyan Chandrasegaran, Milad Abdollahzadeh, Ngai-man Cheung

NeurIPS 2023 · Adversarial robustness and security › Black-box and transfer attacks · approach: Data-free substitute training · 3 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
Transfer target-model decisions into T-ACGAN rather than training the surrogate with target-labeled public images or standard ACGANSurrogate model for CelebA inversion (FaceNet64 target) · CelebAAttack accuracy: 5.87 $\pm$ 1.65 -> 42.07 $\pm$ 3.46Improved
Add data augmentation to balance target-labeled public training data (ablation)Direct I surrogate training · CelebAAttack accuracy: 5.87 $\pm$ 1.65 -> 9.60 $\pm$ 2.22Improved
Add an ensemble of surrogate architectures instead of using one surrogate (ablation)LOKT · CelebA (FaceNet64; CelebA public)Attack accuracy: 92.80 $\pm$ 2.59 -> 93.93 $\pm$ 2.78Improved
Use T-ACGAN's generated, target-labeled data to train a separate surrogate rather than use its discriminator/classifier directly (ablation)LOKT · CelebA (FaceNet64; CelebA public)Attack accuracy: 81.00 $\pm $ 4.79 -> 92.80 $\pm $ 2.59Improved
Use T-ACGAN's generated, target-labeled data to train a separate surrogate rather than its discriminator/classifier directly (ablation)LOKT · Pubfig83 (FaceNet64; Pubfig83 public)Attack accuracy: 74.80 $\pm $ 5.93 -> 61.60 $\pm $ 3.58Hurt
Replace BREPMI's black-box search with LOKT's knowledge-transfer surrogate attackLabel-only model inversion · CelebA (FaceNet64; CelebA public)Attack accuracy: 73.93 $\pm $ 4.98 -> 93.93 $\pm $ 2.78Improved
Replace BREPMI's black-box search with LOKT's knowledge-transfer surrogate attackLabel-only model inversion · CelebA (FaceNet64; FFHQ public)Attack accuracy: 43.00 $\pm$ 5.14 -> 62.07 $\pm$ 3.89Improved
Use LOKT's knowledge-transfer surrogate attack instead of BREPMILabel-only model inversion · CelebA with BiDO-HSIC targetAttack accuracy: 37.40 $\pm$ 3.66 -> 60.73 $\pm$ 3.07Improved
Use LOKT's knowledge-transfer surrogate attack instead of BREPMILabel-only model inversion · CelebA with MID targetAttack accuracy: 39.20 $\pm$ 4.19 -> 60.33 $\pm$ 4.76Improved
Use LOKT's discriminator/classifier surrogate rather than BREPMILabel-only model inversion · CelebA (IR152; CelebA public)Attack accuracy: 71.47 $\pm$ 5.32 -> 72.07 $\pm$ 4.03No clear effect
Use generated surrogate model S instead of the discriminator/classifier for the CelebA inversion setting (ablation)LOKT · CelebA (FaceNet64; FFHQ public)KNN distance: 1516.18 -> 1437.86Improved
Use the ensemble surrogate rather than BREPMILabel-only model inversion · CelebA (FaceNet64; CelebA public; query budget)Queries (millions): 17.98 -> 12.66Improved

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