Soheil Feizi

Porcupine Neural Networks: Approximating Neural Network Landscapes

2018 · Neural Information Processing Systems

Neural networks have been used prominently in several machine learning and statistics applications. In general, the underlying optimization of neural networks is non-convex which makes analyzing their performance challenging. In this paper, we take another …

Wasserstein Smoothing: Certified Robustness against Wasserstein Adversarial Attacks

2019 · arXiv (Cornell University)

In the last couple of years, several adversarial attack methods based on different threat models have been proposed for the image classification problem. Most existing defenses consider additive threat models in which sample perturbations have …

Provable Adversarial Robustness for Fractional Lp Threat Models

2022 · arXiv (Cornell University)

In recent years, researchers have extensively studied adversarial robustness in a variety of threat models, including L_0, L_1, L_2, and L_infinity-norm bounded adversarial attacks. However, attacks bounded by fractional L_p "norms" (quasi-norms defined by the …

Certifiably Robust Policy Learning against Adversarial Communication in Multi-agent Systems

2022 · arXiv (Cornell University)

Communication is important in many multi-agent reinforcement learning (MARL) problems for agents to share information and make good decisions. However, when deploying trained communicative agents in a real-world application where noise and potential attackers exist, …

Temporal Robustness against Data Poisoning

2023 · arXiv (Cornell University)

Data poisoning considers cases when an adversary manipulates the behavior of machine learning algorithms through malicious training data. Existing threat models of data poisoning center around a single metric, the number of poisoned samples. In …