Research map / Adversarial robustness and security / Attacks on text and graphs
Adversary for Social Good: Protecting Familial Privacy through Joint Adversarial Attacks
Chetan Kumar, Riazat Ryan, Ming Shao
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add graph structure (GNN) to visual features for family recognition | SphereNet features · Family-300 | accuracy (%): 17.00 -> 98.89 | Improved |
| joint feature and graph attack versus single attack (ablation) | joint attack · Family-100 and Family-300 | accuracy under attack | Improved |
| perturb face images directly instead of 512D SphereNet features (ablation) | FGSM · Family-100 | accuracy under attack | Improved |
| increase labeled family members or images per person in graph | GCN family recognition · Family-100 | accuracy (%) | Improved |
Closest papers by meaning
- Demystifying Uneven Vulnerability of Link Stealing Attacks against Graph Neural Networks (ICML 2023 · similarity 0.85)
- Value at Adversarial Risk: A Graph Defense Strategy against Cost-Aware Attacks (AAAI 2024 · similarity 0.84)
- Detection and Defense of Unlearnable Examples (AAAI 2024 · similarity 0.83)
- Enhancing Robustness of Graph Neural Networks on Social Media with Explainable Inverse Reinforcement Learning (NeurIPS 2024 · similarity 0.83)
- Adversarial Socialbots Modeling Based on Structural Information Principles (AAAI 2024 · similarity 0.82)
- Enhancing Facial Privacy Protection via Weakening Diffusion Purification (CVPR 2025 · similarity 0.82)
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.
