Search papers, labs, and topics across Lattice.
Minot State University
2
0
3
A controlled benchmark of membership inference vulnerability for text classification on the GLUE SST-2 sentiment dataset is presented and lightweight training adjustments can improve the privacy-utility trade-off without complex defenses.
The results separate indiscriminate poisoning, which shows up in standard metrics, from targeted backdoor poisoning, which stays comparatively stealthy while embedding highly effective malicious behavior, and they support security-oriented evaluation beyond conventional clean-test metrics.
