Yevgeniy Vorobeychik
7 papers in the PaperMetrix corpus
Papers by this author
-
Multi-Defender Strategic Filtering Against Spear-Phishing Attacks
2016 · Proceedings of the AAAI Conference on Artificial Intelligence
Spear-phishing attacks pose a serious threat to sensitive computer systems, since they sidestep technical security mechanisms by exploiting the carelessness of authorized users. A common way to mitigate such attacks is to use e-mail filters …
-
Simple Physical Adversarial Examples against End-to-End Autonomous Driving Models
2019 · arXiv (Cornell University)
Recent advances in machine learning, especially techniques such as deep neural networks, are promoting a range of high-stakes applications, including autonomous driving, which often relies on deep learning for perception. While deep learning for perception …
-
A Semantic Cover Approach for Topic Modeling
2019
We introduce a novel topic modeling approach based on constructing a semantic set cover for clusters of similar documents. Specifically, our approach first clusters documents using their Tf-Idf representation, and then covers each cluster with …
-
Can Optical Trojans Assist Adversarial Perturbations?
2021
Recent work has demonstrated how physically realizable attacks on neural network vision pipelines can consistently produce misclassifications of a given target object. A smaller body of work has also produced modifications that can be applied …
-
Robust Graph Contrastive Learning with Information Restoration
2023 · arXiv (Cornell University)
The graph contrastive learning (GCL) framework has gained remarkable achievements in graph representation learning. However, similar to graph neural networks (GNNs), GCL models are susceptible to graph structural attacks. As an unsupervised method, GCL faces …
-
Conformal Temporal Logic Planning using Large Language Models
2023 · arXiv (Cornell University)
This paper addresses planning problems for mobile robots. We consider missions that require accomplishing multiple high-level sub-tasks, expressed in natural language (NL), in a temporal and logical order. To formally define the mission, we treat …
-
Residual-PAC Privacy: Automatic Privacy Control Beyond the Gaussian Barrier
2025 · arXiv (Cornell University)
The Probably Approximately Correct (PAC) Privacy framework [46] provides a powerful instance-based methodology to preserve privacy in complex data-driven systems. Existing PAC Privacy algorithms (we call them Auto-PAC) rely on a Gaussian mutual information upper …