44 citations · 58 across the 5 of their papers we have counts for
7 papers · 1 filter
Detecting Adversarial Patches with Class Conditional Reconstruction Networks
Perry Deng, Mohammad Saidur Rahman, Matthew Wright
Defending against physical adversarial attacks is a rapidly growing topic in deep learning and computer vision. Prominent forms of physical adversarial attacks, such as overlaid ad…
Weaponizing Unicodes with Deep Learning -- Identifying Homoglyphs with Weakly Labeled Data
Perry Deng, Cooper Linsky, Matthew Wright
Visually similar characters, or homoglyphs, can be used to perform social engineering attacks or to evade spam and plagiarism detectors. It is thus important to understand the capa…
Tik-Tok: The Utility of Packet Timing in Website Fingerprinting Attacks
Mohammad Saidur Rahman, Payap Sirinam, Nate Mathews +2
A passive local eavesdropper can leverage Website Fingerprinting (WF) to deanonymize the web browsing activity of Tor users. The value of timing information to WF has often been di…
Towards Predicting Efficient and Anonymous Tor Circuits
Armon Barton, Mohsen Imani, Jiang Ming +1
The Tor anonymity system provides online privacy for millions of users, but it is slower than typical web browsing. To improve Tor performance, we propose PredicTor, a path selecti…
The Evaluation of Circuit Selection Methods on Tor
Mohsen Imani, Mehrdad Amirabadi, Matthew Wright
Tor provides anonymity online by routing traffic through encrypted tunnels, called circuits, over paths of anonymizing relays. To enable users to connect to their selected destinat…
Forming Guard Sets using AS Relationships
Mohsen Imani, Armon Barton, Matthew Wright
The mechanism for picking guards in Tor suffers from security problems like guard fingerprinting and from performance issues. To address these issues, Hayes and Danezis proposed th…