<ul><li>Data attribution aims to quantify the contribution of individual training data points to the outputs of an AI model.</li><li>A critical question arises regarding the adversarial robustness of data attribution methods.</li><li>Researchers propose two adversarial attack methods, Shadow Attack and Outlier Attack, to manipulate data-attribution-based compensation.</li><li>Empirical results show significant inflation in data-attribution-based compensation using the proposed attack methods.</li></ul>

Adversarial Attacks on Data Attribution

Discover more