125 citations · 311 across the 20 of their papers we have counts for
7 papers · 1 filter
You Do (Not) Belong Here: Detecting DPI Evasion Attacks with Context Learning
Shitong Zhu, Shasha Li, Zhongjie Wang +5
As Deep Packet Inspection (DPI) middleboxes become increasingly popular, a spectrum of adversarial attacks have emerged with the goal of evading such middleboxes. Many of these att…
Connecting the Dots: Detecting Adversarial Perturbations Using Context Inconsistency
Shasha Li, Shitong Zhu, Sudipta Paul +5
There has been a recent surge in research on adversarial perturbations that defeat Deep Neural Networks (DNNs) in machine vision; most of these perturbation-based attacks target ob…
Sharing Models or Coresets: A Study based on Membership Inference Attack
Hanlin Lu, Changchang Liu, Ting He +2
Distributed machine learning generally aims at training a global model based on distributed data without collecting all the data to a centralized location, where two different appr…
Rapid Top-Down Synthesis of Large-Scale IoT Networks
Pradipta Ghosh, Jonathan Bunton, Dimitrios Pylorof +6
Advances in optimization and constraint satisfaction techniques, together with the availability of elastic computing resources, have spurred interest in large-scale network verific…
Topological Effects on Attacks Against Vertex Classification
Benjamin A. Miller, Mustafa Çamurcu, Alexander J. Gomez +2
Vertex classification is vulnerable to perturbations of both graph topology and vertex attributes, as shown in recent research. As in other machine learning domains, concerns about…
Node Immunization with Non-backtracking Eigenvalues
Leo Torres, Kevin S. Chan, Hanghang Tong +1
The non-backtracking matrix and its eigenvalues have many applications in network science and graph mining, such as node and edge centrality, community detection, length spectrum t…
A4 : Evading Learning-based Adblockers
Shitong Zhu, Zhongjie Wang, Xun Chen +6
Efforts by online ad publishers to circumvent traditional ad blockers towards regaining fiduciary benefits, have been demonstrably successful. As a result, there have recently emer…