Integrated Micro and Nano Systems
All our international places for 2026 entry are now filled and we are no longer accepting applications from overseas students
Research Themes
Aim
Our aim is to study trade-offs in image compression algorithms between robustness and several task-specific metrics, like rate, classification error, perception quality, and reconstruction performance, in order to gain insights to develop robust algorithms, with application in extreme compression scenarios, like underwater communication.
Objectives
- Develop a theoretical characterisation of the tradeoffs in image compression between robustness, compression rate, classification error, perception quality, and reconstruction performance.
- Design new image compression algorithms that select features according to the task at end and that are robust to adversarial attacks.
- Validate the algorithms in realistic scenarios, where images undergo extreme compressed due to limitations in bandwidth, as in underwater communication.
Description
Deep neural networks (DNNs) have become essential tools in automated decision-making, powering applications from image classification and segmentation to anomaly detection and portfolio allocation. However, DNNs are notoriously vulnerable to adversarial attacks, prompting extensive research over the past decade to develop new attacks and defense strategies [1-4]. Whilst implementing these defenses can reduce performance on non-perturbed samples [5-7], their impact on multi-task performance remains unclear.
In this project, we explore image compression and decompression algorithms where the target image serves various tasks, such as classification, segmentation, or multimedia. By leveraging knowledge of these downstream tasks, the encoder can select better features and achieve improved compression rates [8]. However, there are inherent trade-offs between compression rates and task performance [9]. Our goal is to study how adversarial attacks influence these tradeoffs, design robust mechanisms for the entire pipeline, for example, leveraging semantically-meaningful representations, and demonstrate the application of these algorithms in scenarios requiring extreme compression ratios, such as underwater communication.
Applications
First-round applications have closed and the applications for SPADS are now being considered on a gathered field basis, where applications will be considered at the end of every month until all places are filled.
[1] C. Szegedy, W. Zaremba, I. Sutskever, J. Bruna, D. Erhan, I. Goodfellow, R. Fergus, "Intriguing Properties Of Neural Networks," arXiv:1312.6199v4, 2014.
[2] N. Akhtar, A. Mian, N. Kardan, and M. Shah, ‘Advances in Adversarial Attacks and Defenses in Computer Vision: A Survey’, IEEE Access, vol. 9, pp. 155161–155196, 2021, doi: 10.1109/ACCESS.2021.3127960.
[3] A. Modas, R. Sanchez-Matilla, P. Frossard, and A. Cavallaro, ‘Toward Robust Sensing for Autonomous Vehicles: An Adversarial Perspective’, IEEE Signal Process. Mag., vol. 37, no. 4, pp. 14-23, Jul. 2020, doi: 10.1109/MSP.2020.2985363.
[4] D. Hendrycks, S. Basart, N. Mu, S. Kadavath, F. Wang, E. Dorundo, R. Desai, T. Zhu, et al., "The Many Faces Of Robustness: A Critical Analysis Of Out-of-Distribution Generalization," ICCV, pp. 8340-8349, 2021.
[5] D. Tsipras, S. Santurkar, L Engstrom, A. Turner, A. Madry, "Robustness May Be at Odds with Accuracy," ICLR, 2019.
[6] H. Zhang, Y. Yu, J. Jiao, E. Xing, L. El Ghaoui, M. Jordan, "Theoretically Principled Tradeoff Between Robustness and Accuracy," ICML, PMLR 97:7472-7482, 2019.
[7] M. Mehrabi, A. Javanmard, R. A. Rossi, A. Rao, T. Mai, "Fundamental Tradeoffs in Distributionally Adversarial Training," ICML, 2021.
[8] Z. Lei, P. Duan, X. Hong, J. F. C. Mota, J. Shi, and C.-X. Wang, "Progressive Deep Image Compression for Hybrid Contexts of Image Classification and Reconstruction", IEEE J. Select. Areas Commun., vol. 41, no. 1, pp. 72–89, Jan. 2023, doi: 10.1109/JSAC.2022.3221998.
[9] J. Fang, J. F. C. Mota, B. Lu, W. Zhang, and X. Hong, "The Rate-Distortion-Perception-Classification Tradeoff: Joint Source Coding and Modulation via Inverse-Domain GANs", IEEE Trans. Signal Process., vol. 72, pp. 3076-3090, 2024, doi: 10.1109/TSP.2024.3411692.
[10] A. Wheeldon and A. Serb, "A study on the clusterability of latent representations in image pipelines," Front. Neuroinform, vol. 17, no. 1074653, pp. 1-11, 2023. doi: 10.3389/fninf.2023.1074653
Minimum entry qualification - an Honours degree at 2:1 or above (or International equivalent) in a relevant science or engineering discipline, possibly supported by an MSc Degree. Further information on English language requirements for EU/Overseas applicants.
Home rate fees and stipend are available for this position.
All our international places for 2026 entry are now filled and we are no longer accepting applications from overseas students
Research Theme
Aim
To develop a low-power, organic photovoltaic (OPV)-integrated, disposable sensor platform that detects trace vapours associated with explosives and common environmental gases (NOx, NH₃, CO and VOCs) for resilient, distributed monitoring.
Objectives
- Design and print a multi-modal sensing array (chemiresistive) with selective coatings for nitroaromatics, taggants and key environmental gases.
- Develop an OPV power-management system and low-power electronics to enable duty-cycled, ≥24-hour autonomous operation under realistic illumination.
- Develop machine learning and pattern-recognition methods to classify sensor responses, enhance selectivity, and minimise false alarms under variable environmental conditions.
- Validate performance with safe simulants in the lab.
Description
This project will develop a compact, low-power sensor node that integrates printed organic photovoltaics (OPV) with a multi-modal array of disposable chemiresistive and electrochemical sensing elements to detect trace vapours from nitroaromatics, explosive taggants, and key environmental gases including NOx, ammonia, carbon monoxide and common VOCs. Functionalized carbon-nanomaterial and molecularly imprinted polymer coatings will provide selective uptake, while machine learning and pattern-recognition algorithms will fuse multi-sensor responses to maximise sensitivity, discriminate analytes, and reduce false alarms. To ensure sustainability, devices will be designed to safely disintegrate into soil after use, building on Dr Panidi’s expertise in organic electronics. A key challenge for low-cost sensors is accuracy in complex, dynamic environments; to address this, deep learning approaches such as convolutional neural networks (CNNs) will enhance feature extraction and enable robust, real-time pollutant classification, drawing on Dr Yang’s expertise. This project couples sustainable sensor design with AI-driven analytics, directly supporting DSTL’s priorities in scalable, secure environmental sensing for public health and national resilience.
Applications
First-round applications have closed and the applications for SPADS are now being considered on a gathered field basis, where applications will be considered at the end of every month until all places are filled.
Minimum entry qualification - an Honours degree at 2:1 or above (or International equivalent) in a relevant science or engineering discipline, possibly supported by an MSc Degree. Further information on English language requirements for EU/Overseas applicants.
Full funding is available for this position.