Research map / Adversarial robustness and security / Attacks on text and graphs
[Re] Exacerbating Algorithmic Bias through Fairness Attacks
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Use the Influence Attack on Fairness (IAF) | Poisoning attacks · German Credit, COMPAS, and Drug Consumption | fairness measures (SPD and EOD) | Helped |
| Use IAF instead of the Solans et al. attack | Poisoning attacks · German Credit, COMPAS, and Drug Consumption | fairness measures (SPD and EOD) | Helped |
| Use an anchoring attack instead of the Solans et al. attack | Poisoning attacks · German Credit, COMPAS, and Drug Consumption | fairness measures (SPD and EOD) | Mixed |
| Target fairness rather than accuracy with the attack loss | Influence Attack (Koh et al.) · German Credit, COMPAS, and Drug Consumption | fairness measures (SPD and EOD) | Helped |
| Increase the IAF loss regularization parameter lambda (ablation) | Influence Attack on Fairness (IAF) · German Credit, COMPAS, and Drug Consumption | fairness measures (SPD and EOD) | Helped |
| Use lower lambda values (ablation) | Influence Attack on Fairness (IAF) · German Credit, COMPAS, and Drug Consumption | accuracy | Mixed |
| Increase the poison fraction epsilon (ablation) | Influence Attack on Fairness (IAF) · German Credit, COMPAS, and Drug Consumption | fairness measures (SPD and EOD) | Helped |
Closest papers by meaning
- Searching for Unfairness in Algorithms’ Outputs: Novel Tests and Insights (AAAI 2025 · similarity 0.85)
- Identifying Reasons for Bias: An Argumentation-Based Approach (AAAI 2024 · similarity 0.85)
- Intersectional Fairness via Mixed-Integer Optimization (NeurIPS 2026 · similarity 0.85)
- An Information-Flow Perspective on Algorithmic Fairness (AAAI 2024 · similarity 0.84)
- Fairness Shields: Safeguarding against Biased Decision Makers (AAAI 2025 · similarity 0.84)
- Fairness under Competition (NeurIPS 2025 · similarity 0.84)
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.