A new data-poisoning audit framework has been developed for causal effect estimation in observational studies. This framework allows analysts to specify feasible records, append budgets, and source capacities, enabling adversaries to strategically select records to alter reported treatment effects. The proposed method includes a greedy scan for exact worst-case movement and a total-influence score to account for nuisance refitting, providing a more reliable approach to causal reporting and the design of safeguards. AI
IMPACT Enhances the reliability of causal inference in AI models by providing tools to detect and mitigate data manipulation.
RANK_REASON The cluster contains a research paper detailing a new methodology for data-poisoning audits in causal effect estimation. [lever_c_demoted from research: ic=1 ai=1.0]
- alphaXiv
- arXiv
- CatalyzeX
- Connected Papers
- DagsHub
- Gotit.pub
- Hugging Face
- Influence Flower
- Litmaps
- ScienceCast
- scite Smart Citations
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →
