Page Information

Versions Compared


  • This line was added.
  • This line was removed.
  • Formatting was changed.


Author Obfuscation using Differential Privacy

 On April 6 Natasha Fernandes presented her MRes thesis work on A Novel Framework for Author Obfuscation using Generalised Differential Privacy.

Abstract: The problem of obfuscating the authorship of a text document has received little attention in the literature to date. Current approaches are ad-hoc and rely on assumptions about an adversary’s auxiliary knowledge which makes it difficult to reason about the privacy properties of these methods. Differential privacy is a well-known and robust privacy approach, but its reliance on the notion of adjacency between datasets has prevented its application to text document privacy to date. A relatively new approach to privacy known as generalised differential privacy extends differential privacy to arbitrary datasets endowed with a metric and permits the private release of individual data points. In this paper we show how to apply generalised differential privacy to author obfuscation, utilising existing tools and methods from the stylometry and natural language processing literature.

Learning Computing

On April 13 we discussed the following two papers:

On March 16 we discussed the following paper: Abstraction ability as an indicator of success for learning computing science? by Bennedssen and Caspersen.


 On March 9 we discussed two short papers about the applications and use of WebAssembly:

On March 2 we discussed the paper Mechanising and Verifying the WebAssembly Specification by Watt. More information on WebAssembly can be found at the project site.

On February 23 we discussed the paper Bringing the web up to speed with WebAssembly by Haas et al. More information on WebAssembly can be found at the project site.

Safety-Critical Use of a Formally-Verified Compiler 

On January 19 we discussed the paper CompCert: Practical Experience on Integrating and Qualifying a Formally Verified Optimizing Compiler by Kästner et al.