• Publications
  • Influence
Cirripede: circumvention infrastructure using router redirection with plausible deniability
Many users face surveillance of their Internet communications and a significant fraction suffer from outright blocking of certain destinations. Anonymous communication systems allow users to concealExpand
  • 125
  • 15
Multi-flow Attacks Against Network Flow Watermarking Schemes
We analyze several recent schemes for watermarking network flows based on splitting the flow into intervals. We show that this approach creates time dependent correlations that enable an attack thatExpand
  • 84
  • 15
SWIRL: A Scalable Watermark to Detect Correlated Network Flows
Flow watermarks are active traffic analysis techniques that help establish a causal connection between two network flows by content-independent manipulations, e.g., altering packet timings.Expand
  • 92
  • 13
The Parrot Is Dead: Observing Unobservable Network Communications
In response to the growing popularity of Tor and other censorship circumvention systems, censors in non-democratic countries have increased their technical capabilities and can now recognize andExpand
  • 153
  • 12
Stegobot: A Covert Social Network Botnet
We propose Stegobot, a new generation botnet that communicates over probabilistically unobservable communication channels. It is designed to spread via social malware attacks and steal informationExpand
  • 86
  • 11
I want my voice to be heard: IP over Voice-over-IP for unobservable censorship circumvention
Open communication over the Internet poses a serious threat to countries with repressive regimes, leading them to develop and deploy censorship mechanisms within their networks. Unfortunately,Expand
  • 84
  • 11
RAINBOW: A Robust And Invisible Non-Blind Watermark for Network Flows
Linking network flows is an important problem in intrusion detection as well as anonymity. Passive traffic analysis can link flows but requires long periods of observation to reduce errors.Expand
  • 114
  • 9
Machine Learning with Membership Privacy using Adversarial Regularization
Machine learning models leak significant amount of information about their training sets, through their predictions. This is a serious privacy concern for the users of machine learning as a service.Expand
  • 93
  • 9
Comprehensive Privacy Analysis of Deep Learning: Stand-alone and Federated Learning under Passive and Active White-box Inference Attacks
Deep neural networks are susceptible to various inference attacks as they remember information about their training data. We perform a comprehensive analysis of white-box privacy inference attacks onExpand
  • 51
  • 8
No Direction Home: The True Cost of Routing Around Decoys
Decoy routing is a recently proposed approach for censorship circumvention. It relies on cooperating ISPs in the middle of the Internet to deploy the so called “decoy routers” that proxy networkExpand
  • 46
  • 7