Yuxin Wen

Towards Understanding the Regularization of Adversarial Robustness on\n Neural Networks

2020 · arXiv (Cornell University)

The problem of adversarial examples has shown that modern Neural Network (NN)\nmodels could be rather fragile. Among the more established techniques to solve\nthe problem, one is to require the model to be {\\it $\\epsilon$-adversarially\nrobust} (AR); …

Fishing for User Data in Large-Batch Federated Learning via Gradient Magnification

2022 · arXiv (Cornell University)

Federated learning (FL) has rapidly risen in popularity due to its promise of privacy and efficiency. Previous works have exposed privacy vulnerabilities in the FL pipeline by recovering user data from gradient updates. However, existing …

Seeing in Words: Learning to Classify through Language Bottlenecks

2023 · arXiv (Cornell University)

Neural networks for computer vision extract uninterpretable features despite achieving high accuracy on benchmarks. In contrast, humans can explain their predictions using succinct and intuitive descriptions. To incorporate explainability into neural networks, we train a …

Be like a Goldfish, Don't Memorize! Mitigating Memorization in Generative LLMs

2024 · arXiv (Cornell University)

Large language models can memorize and repeat their training data, causing privacy and copyright risks. To mitigate memorization, we introduce a subtle modification to the next-token training objective that we call the goldfish loss. During …