Project Description: Backdoors refer to a class of Machine Learning (ML) attacks where an adversary trains an ML model to intentionally misclassify any input to a specific label [1]. This is typically achieved by poisoning the training data, such that inputs are misclassified to a target label when the backdoor trigger is present. For instance, … full description “Attacking Large Pre-trained Programming Language Models (PLMs) via Backdoors (ongoing)”
Project List
Automated Debugging of Invalid Inputs generated by Fuzzers (ongoing)
Project Description: Fuzzing is a popular testing method used to ensure the reliability, security and correctness of software systems. These tools allow developers to find bugs and vulnerabilities in software systems automatically. For instance, AFL is a popular fuzzer that has exposed thousands of bugs in open-source software provided by Google, Amazon and Firefox [1]. … full description “Automated Debugging of Invalid Inputs generated by Fuzzers (ongoing)”
Cough recognition system (ongoing)
The project requires the automated sorting of files and Raspberry Pi implementation of a Matlab trained CNN model for cough recognition and storage. This will involve acquiring data from a low-cost IoT based processing system (Raspberry Pi) connected to a network of CO2, temperature, humidity, PM 2.5 and sound sensors array. This project would suit … full description “Cough recognition system (ongoing)”
Engineering ROTOR: a Refactoring Tool for OCaml (ongoing)
OCaml [1] is a mature functional programming language with an expressive type system. Recently, we have developed a prototype tool, called ROTOR, for automatically refactoring OCaml codebases [2]. Currently, ROTOR handles renaming of functions. This is surprisingly hard due to OCaml’s powerful module system: renaming a function in one module may actually require renaming functions … full description “Engineering ROTOR: a Refactoring Tool for OCaml (ongoing)”
Natural Language Understanding: Measuring the Semantic Similarity between Sentences (ongoing)
Overview To implement and design various deep neural networks for measuring the semantic similarities between sentence pairs. Background Natural language understanding (NLU) is widely viewed as a grand challenge in Artificial Intelligence (AI). An important sub-task in NLU is to measure the semantic similarity between sentence pairs, also known as the Semantic Textual Similarity (STS) task. A … full description “Natural Language Understanding: Measuring the Semantic Similarity between Sentences (ongoing)”