Cybersecurity is an ongoing arms race between attackers and security researchers. Therefore, it is not only important to simply build algorithms, tools, and systems addressing various scenarios but also to update and adapt them to the ever-changing cyber threat landscape.
Our team has strong expertise in characterising and exposing cyber risks through empirical studies, developing AI and machine learning based security solutions, and developing secure systems.
Phishing is an ongoing internet problem being increasingly used to steal personal information, spread malware, and penetrate corporate networks. Targeted phishing attempts may be able to mislead even the most tech-savvy users if they are not on alert. Existing solutions majorly focus on the similarity of the textual content of emails and web pages. However, sophisticated phishing attempts can prompt users with highly visually similar interfaces and forged content to present misleading information.
This project develops a phishing detection system based on the visual similarity of websites at internet-scale by leveraging the recent advances in deep learning. Our project is funded by the Pilot Grant Scheme of the NSW cyber security network. A related project of detecting mobile phishing attempts was funded by the 2017 Google Faculty Rewards Scheme.
Our partners: Professor Mahbub Hassan (University of New South Wales)
With the advent of the Internet of Things (IoT), a myriad of devices are increasingly being installed in our physical environment, and connected to cloud-based services via the internet. This rollout though has happened with little concern for security. Governments, industry, and consumers face a grand challenge: with IoT technology proposed or already in use in Industry 4.0, smart cities, smart homes, and many other fields, the very same devices may well be vulnerable to attack. The potential for serious damage, nationally and globally, is enormous – yet too little is known about the actual attack surface and the real threat landscape.
The goal of this project is to address these uncertainties by carrying out empirical security measurements and assess what attack vectors are possible, already being tried, and which risks the devices’ connection to the cloud is exposed to.
Our experts: Dr Suranga Seneviratne, Dr Kanchana Thilakarathna
Our partners: Dr Guillaume Jourjon (Data61 / CSIRO), Dr Adriel Chang (Defence Science and Technology Group), Mr Darren Webb (Defence Science and Technology Group), Associate Professor Richard Xu (UTS)
Providers of large, enterprise-class networks find it hard to track hosts, servers and other vulnerable assets in their networks. Network profiling systems provide valuable insight of the assets on a network and their purpose. A network profile enables providers to better consider how configuration changes will impact networks, and security administrators to identify suspicious activity. However, effective network profiling under real world conditions is increasingly challenging. Network speeds are continually increasing and use of encryption is growing.
Project Deep Bypass will develop tools for profiling enterprise-class networks. This set of tools ranges from capturing network traffic at high-speed without altering information contained in the traffic, to the development of new traffic profiling techniques capable of understand both encrypted and clear traffic using deep learning algorithms on top of untrusted data. Overall this eclectic set of tools will be implemented using newly developed distributed architecture capable of leveraging the high level of concurrency in modern CPUs.
Our partners: Professor Michel Raynal (IRISA, ISTIC Université de Rennes, France)
We are developing a new blockchain aimed at providing “Trust Among Individual ParticipANts” (TAIPAN). The main feature of TAIPAN’s programmable blockchain is the integrity and security of individual ownership records that current blockchains lack.
Our team combines expertise from security, distributed computing, programming languages, and data management to overcome two major threats in current programmable blockchains: (1) double-spending among participants, and (2) security vulnerabilities in smart contracts. TAIPAN provides a democratic and leaderless consensus algorithm that avoids double-spending, and a new bug-checking framework for smart contracts that finds anomalies before smart contracts are admitted to the blockchain. Rigorous empirical analysis supports our security and performance goals