🔐 ML Security Journal Club

✅ This Week's Presentation:

🔹 Title: Robust Machine Unlearning for Quantized Neural Networks via Adaptive Gradient Reweighting with Similar Labels

🔸 Presenter: Arian Komaei

🌀 Abstract:

This paper studies machine unlearning (MU) in quantized neural networks, where conventional unlearning methods designed for full-precision models can become significantly less effective. The authors identify two key challenges introduced or amplified by quantization: noise from randomly relabeling forgotten samples and gradient imbalance between forgotten and retained data. Because quantized models operate in a constrained, discrete parameter space, these effects can lead to unstable updates and poorer approximation of a model retrained from scratch.
To address these issues, the authors propose Q-MUL, a quantization-aware unlearning framework with two main components. Similar Labels (SL) replaces random labels for forgotten samples with alternative labels selected according to the model's current output distribution, reducing disruptive noise during unlearning. Adaptive Gradient Reweighting (AGR) dynamically balances the contributions of forgotten and retained data according to their gradient norms.
Experiments on datasets including CIFAR-10, CIFAR-100, SVHN, and Tiny-ImageNet, using quantized ResNet-18 and MobileNetV2, show that Q-MUL generally produces models whose forgetting, retention, test accuracy, and membership-inference behavior are closer to those of models retrained from scratch than existing approximate-unlearning baselines.

📄 Paper: Robust Machine Unlearning for Quantized Neural Networks via Adaptive Gradient Reweighting with Similar Labels

Session Details:
📅 Date: Sunday یک‌شنبه
🕒 Time: 6:00 – 7:00 PM
🌐 Location: Online at vc.sharif.edu/ch/rohban

We look forward to your participation! ✌️