AdvPaint: Protecting Images from Inpainting Manipulation via Adversarial Attention Disruption.

You Only Perturb Once: Bypassing (Robust) Ad-Blockers Using Universal Adversarial Perturbations

Targeted Model Inversion: Distilling style encoded in predictions

Effective Targeted Attacks for Adversarial Self-Supervised Learning

AdCPG: Classifying JavaScript Code Property Graphs with Explanations for Ad and Tracker Blocking

Margin-based Neural Network Watermarking.

RICC: Robust Collective Classification of Sybil Accounts.

DiffCSP: Finding Browser Bugs in Content Security Policy Enforcement through Differential Testing.

Scalable and Secure Virtualization of HSM with ScaleTrust

Learning to Generate Inversion-Resistant Model Explanations.