AI Paper Atlas

Research map / Adversarial robustness and security / Attacks on text and graphs

Bucks for Buckets (B4B): Active Defenses Against Stealing Encoders

Jan Dubiński, Stanisław Pawlak, Franziska Boenisch, Tomasz Trzcinski, Adam Dziedzic

NeurIPS 2023 · Adversarial robustness and security › Attacks on text and graphs · approach: Membership inference and inversion · 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
Use coverage-adaptive noise and per-user transformations instead of returning unmodified representationsSimSiam ResNet50 API · CIFAR10, STL10, SVHN, and FashionMNIST legitimate-user tasksaccuracy: 90.41{ $\pm$0.02} -> 90.24{ $\pm$0.11}; 95.08{ $\pm$0.13} -> 95.05{ $\pm$0.1}; 75.47{ $\pm$0.04} -> 74.96{ $\pm$0.13}; 9No clear effect
Steal through B4B-protected API rather than an undefended APISimSiam ResNet50 · CIFAR10, STL10, SVHN, and FashionMNIST; 50K ImageNet queriesaccuracy: 65.2{ $\pm$0.03} -> 35.72{ $\pm$0.04}; 64.9{ $\pm$0.01} -> 31.54{ $\pm$0.02}; 63.1{ $\pm$0.01} -> 19.74{ $\pm$0.02}; 88.Hurt
Increase stealing queries from 50K to 100K through the B4B-protected APISingle-account attacker · CIFAR10, STL10, SVHN, and FashionMNIST; ImageNet queriesaccuracy: CIFAR10: 35.72{ $\pm$0.04} -> 12.01{ $\pm$0.07}; STL10: 31.54{ $\pm$0.02} -> 13.94{ $\pm$0.05}; SVHN: 19.74{ $\pm$0.02} Mixed
Steal with LAION instead of ImageNet queries through B4BSimSiam ResNet50 · CIFAR10 downstream task; 100K queriesaccuracy: 64.92{ $\pm$0.03} -> 40.96{ $\pm$ 0.03}Hurt
Use two sybil accounts and remap their representationsB4B-protected SimSiam stealing attack · ImageNet stealing; downstream classification tasksaccuracy: CIFAR10: 39.56{ $\pm$ 0.06}; STL10: 38.50{ $\pm$0.04}; SVHN: 23.41{ $\pm$0.02}; FashionMNIST: 77.01{ $\pm$ 0.08}Mixed
Increase the number of sybil accounts from two to more accountsB4B-protected stealing attack · ImageNet stealing; downstream classification tasksaccuracy: 2$\times$50k: 39.56{ $\pm$ 0.06}; 6$\times$16.7k: 26.62{ $\pm$ 0.04}Hurt
Replace B4B with static noise at sigma 0.1 (ablation)SimSiam API and 50K-query attacker · CIFAR10accuracy: Legitimate: 90.41 { $\pm$0.02} -> 90.20{ $\pm$0.03}; attacker: 65.2{ $\pm$0.03} -> 64.92{ $\pm$0.04}No clear effect
Replace B4B with static noise at sigma 10 (ablation)SimSiam API and 50K-query attacker · CIFAR10accuracy: Legitimate: 90.41 { $\pm$0.02} -> 65.11{ $\pm$0.45}; attacker: 65.2{ $\pm$0.03} -> 36.32{ $\pm$0.2}Mixed
Use Binary rather than no transformation (ablation)SimSiam representations for legitimate CIFAR10 users · CIFAR10accuracy: 90.41\% ($\pm$ 0.02) -> 88.78\% ($\pm$ 0.2)Hurt
Increase lambda to 10^-4 from 10^-6 while keeping alpha=1 and beta=80% (ablation)B4B cost function · Legitimate downstream tasks and ImageNet stealingaccuracy: Legitimate CIFAR10: 90.41{ $\pm$0.02} -> 90.02 { $\pm$0.1}; 50K attacker CIFAR10: 65.2 { $\pm$0.03} -> 28.22 { $\pm$ 0.0Mixed
Reduce beta from 50% to 30% (ablation)B4B cost function · Legitimate CIFAR10 and 100K ImageNet stealingaccuracy: Legitimate CIFAR10: 90.27 { $\pm$0.07} -> 88.1 { $\pm$0.11}; attacker CIFAR10: 16.27 { $\pm$ 0.04} -> 9.57 { $\pm$ 0.17}Mixed
Reduce alpha from 1 to 0.1 while keeping beta=30% and lambda=10^-6 (ablation)B4B cost function · Legitimate CIFAR10 downstream taskaccuracy: 88.1 { $\pm$0.11} -> 90.17 { $\pm$0.1}Improved

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