A
Amir Rahmati
Researcher at Stony Brook University
Publications - 41
Citations - 3726
Amir Rahmati is an academic researcher from Stony Brook University. The author has contributed to research in topics: Computer science & Overhead (computing). The author has an hindex of 19, co-authored 37 publications receiving 2643 citations. Previous affiliations of Amir Rahmati include University of Michigan & University of Massachusetts Amherst.
Papers
More filters
Proceedings ArticleDOI
Robust Physical-World Attacks on Deep Learning Visual Classification
Kevin Eykholt,Ivan Evtimov,Earlence Fernandes,Bo Li,Amir Rahmati,Chaowei Xiao,Atul Prakash,Tadayoshi Kohno,Dawn Song +8 more
TL;DR: This work proposes a general attack algorithm, Robust Physical Perturbations (RP2), to generate robust visual adversarial perturbations under different physical conditions and shows that adversarial examples generated using RP2 achieve high targeted misclassification rates against standard-architecture road sign classifiers in the physical world under various environmental conditions, including viewpoints.
Posted Content
Robust Physical-World Attacks on Machine Learning Models.
Ivan Evtimov,Kevin Eykholt,Earlence Fernandes,Tadayoshi Kohno,Bo Li,Atul Prakash,Amir Rahmati,Dawn Song +7 more
TL;DR: This paper proposes a new attack algorithm--Robust Physical Perturbations (RP2)-- that generates perturbations by taking images under different conditions into account and can create spatially-constrained perturbation that mimic vandalism or art to reduce the likelihood of detection by a casual observer.
Proceedings ArticleDOI
ContexIoT: Towards Providing Contextual Integrity to Appified IoT Platforms
Yunhan Jia,Qi Alfred Chen,Shiqi Wang,Amir Rahmati,Earlence Fernandes,Z. Morley Mao,Atul Prakash +6 more
TL;DR: ContexIoT is proposed, a context-based permission system for appified IoT platforms that provides contextual integrity by supporting fine-grained context identification for sensitive actions, and runtime prompts with rich context information to help users perform effective access control.
Proceedings Article
FlowFence: practical data protection for emerging IoT application frameworks
TL;DR: FlowFence is presented, a system that requires consumers of sensitive data to declare their intended data flow patterns, which it enforces with low overhead, while blocking all other undeclared flows.
Posted Content
Physical Adversarial Examples for Object Detectors
Kevin Eykholt,Ivan Evtimov,Earlence Fernandes,Bo Li,Amir Rahmati,Florian Tramèr,Atul Prakash,Tadayoshi Kohno,Dawn Song +8 more
TL;DR: In this article, the authors extend physical attacks to more challenging object detection models, a broader class of deep learning algorithms widely used to detect and label multiple objects within a scene, and demonstrate the transferability of their adversarial perturbations.