We highlight the importance of using dynamic FR strategies to evaluate AFR methods, and propose DivTrackee as a promising countermeasure.

We show how prior claims about black-box access sufficing for optimal membership inference do not hold for most useful settings such as SGD, and validate our findings with a new white-box inference attack.

Understand the inherent vulnerabilities to indiscriminate data poisoning attacks for linear learners by studying the optimal poisoning strategy from the perspective of data distribution.

Built upon on a novel definition of label uncertainty, we develop an empirical method to estimate a more realistic intirnsic robustness limit for image classification tasks.

We develop a method to measure the concentration of image benchmarks using empirical samples and show that concentration of measure does not prohibit the existence of adversarially robust classifiers.