cd/entity/U-LiRA· home› entities› U-LiRA
grep -l @u-lira /news/*.json | wc -l → 1

U-LiRA

mentions 1 type Organization feed RSS

// recent coverage 1 mentions

09:09
2026-07-14
machinebrief.com
artificial-intelligence

New AI Method Tackles Privacy Leaks in Unlearning

MIT researchers have developed Tilted REWeighting (TREW), a method that fixes privacy leaks in AI class unlearning by adjusting the model's distribution to mimic a scratch-trained model. On CIFAR-10, …

// co-occurs with top 4 entities
MIT 1 Tilted REWeighting 1 CIFAR-10 1 CMIA 1
// topics top 4 topics
artificial intelligence 1 ai safety 1 ai ethics 1 machine learning 1