206 citations · 293 across the 7 of their papers we have counts for
7 papers
Group-based Robustness: A General Framework for Customized Robustness in the Real World
Weiran Lin, Keane Lucas, Neo Eyal +3
Machine-learning models are known to be vulnerable to evasion attacks that perturb model inputs to induce misclassifications. In this work, we identify real-world scenarios where t…
Scalable Verification of GNN-based Job Schedulers
Haoze Wu, Clark Barrett, Mahmood Sharif +2
Recently, Graph Neural Networks (GNNs) have been applied for scheduling jobs over clusters, achieving better performance than hand-crafted heuristics. Despite their impressive perf…
Constrained Gradient Descent: A Powerful and Principled Evasion Attack Against Neural Networks
Weiran Lin, Keane Lucas, Lujo Bauer +2
We propose new, more efficient targeted white-box attacks against deep neural networks. Our attacks better align with the attacker's goal: (1) tricking a model to assign higher pro…
-ML: Mitigating Adversarial Examples via Ensembles of Topologically Manipulated Classifiers
Mahmood Sharif, Lujo Bauer, Michael K. Reiter
This paper proposes a new defense called -ML against adversarial examples, i.e., inputs crafted by perturbing benign inputs by small amounts to induce misclassifications by clas…
Malware Makeover: Breaking ML-based Static Analysis by Modifying Executable Bytes
Keane Lucas, Mahmood Sharif, Lujo Bauer +2
Motivated by the transformative impact of deep neural networks (DNNs) in various domains, researchers and anti-virus vendors have proposed DNNs for malware detection from raw bytes…
On the Suitability of -norms for Creating and Preventing Adversarial Examples
Mahmood Sharif, Lujo Bauer, Michael K. Reiter
Much research effort has been devoted to better understanding adversarial examples, which are specially crafted inputs to machine-learning models that are perceptually similar to b…
A General Framework for Adversarial Examples with Objectives
Mahmood Sharif, Sruti Bhagavatula, Lujo Bauer +1
Images perturbed subtly to be misclassified by neural networks, called adversarial examples, have emerged as a technically deep challenge and an important concern for several appli…