Alberto Marchisio

Achievements

Alberto Marchisio – DC-RES Final Report

Awards and Achievements

• Runner-up for the 2023 International Neural Network Society Doctoral Dissertation Award, IEEE WCCI 2024.
• Future Internet 2022 Best Paper Award for the paper “An Updated Survey of Efficient Hardware Architectures for Accelerating Deep Convolutional Neural Networks” in MDPI Future Internet, 2020.
• D. Forum at the 41st International Symposium on Reliable Distributed System (Ph.D. Forum @ SRDS), 2022.
• D. Forum at the 25th Design, Automation and Test in Europe Conference (Ph.D. Forum @ DATE), 2022.
• D. Forum at the 58th Design Automation Conference (Ph.D. Forum @ DAC), 2021.
• Student Research Forum at the 26th Asia and South Pacific Design Automation Conference (SRF @ ASP-DAC), 2021.
• IEEE CIS Conference Travel Grant for Graduate Students – IEEE IJCNN 2023.
• IEEE CIS Conference Participation and Travel Grant for Graduate Students – IEEE WCCI 2022.
• IEEE CIS Conference Registration Grant for Graduate Students – IEEE WCCI 2020.

Publications included in the Ph.D. Thesis

Conference Publications

[C1]       A. Marchisio, B. Bussolino, A. Colucci, M. Martina, G. Masera, and M. Shafique, “Q-CapsNets: A Specialized Framework for Quantizing Capsule Networks,” in 57th ACM/IEEE Design Automation Conference, DAC 2020, San Francisco, CA, USA, July 20-24, 2020, pp. 1–6, IEEE, 2020. Received a HiPEAC Paper Award.

[C2]       A. Marchisio, A. Massa, V. Mrazek, B. Bussolino, M. Martina, and M. Shafique, “NASCaps: A Framework for Neural Architecture Search to Optimize the Accuracy and Hardware Efficiency of Convolutional Capsule Networks,”’ in IEEE/ACM International Conference On Computer Aided Design, ICCAD 2020, San Diego, CA, USA, November 2-5, 2020}, pp. 114:1–114:9, IEEE, 2020.

[C3]       A. Marchisio, G. Pira, M. Martina, G. Masera, and M. Shafique, “R-SNN: An Analysis and Design Methodology for Robustifying Spiking Neural Networks against Adversarial Attacks through Noise Filters for Dynamic Vision Sensors,” in IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2021, Prague, Czech Republic, September 27 – Oct. 1, 2021, pp. 6315–6321, IEEE, 2021.

[C4]       A. Viale, A. Marchisio, M. Martina, G. Masera, and M. Shafique, “LaneSNNs: Spiking Neural Networks for Lane Detection on the Loihi Neuromorphic Processor,” in IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2022, Kyoto, Japan, October 23-27, 2022, pp. 79-86, IEEE, 2022.

[C5]       A. Marchisio, M. A. Hanif, and M. Shafique, “CapsAcc: An Efficient Hardware Accelerator for CapsuleNets with Data Reuse,” in Design, Automation & Test in Europe Conference & Exhibition, DATE 2019, Florence, Italy, March 25-29, 2019, pp. 964–967, IEEE, 2019.

[C6]       A. Marchisio, V. Mrazek, M. A. Hanif, and M. Shafique, “ReD-CaNe: A Systematic Methodology for Resilience Analysis and Design of Capsule Networks under Approximations,” in Design, Automation & Test in Europe Conference & Exhibition, DATE 2020, Grenoble, France, March 9-13, 2020, pp. 1205–1210, IEEE, 2020.

[C7]       R. El-Allami, A. Marchisio, M. Shafique, and I. Alouani, “Securing Deep Spiking Neural Networks against Adversarial Attacks through Inherent Structural Parameters,” in Design, Automation & Test in Europe Conference & Exhibition, DATE 2021, Grenoble, France, February 1-5, 2021, pp. 774–779, IEEE, 2021.

[C8]       A. Marchisio, B. Bussolino, E. Salvati, M. Martina, G. Masera, and M. Shafique, “Enabling Capsule Networks at the Edge through Approximate Softmax and Squash Operations,” in International Symposium on Low Power Electronics and Design, ISLPED 2022, Boston, MA, USA, Aug 1-3, 2022, IEEE, 2022.

[C9]       R. Massa, A. Marchisio, M. Martina, and M. Shafique, “An Efficient Spiking Neural Network for Recognizing Gestures with a DVS Camera on the Loihi Neuromorphic Processor,” in 2020 International Joint Conference on Neural Networks, IJCNN 2020, Glasgow, United Kingdom, July 19-24, 2020, pp. 1–9, IEEE, 2020.

[C10]     A. Marchisio, G. Nanfa, F. Khalid, M. A. Hanif, M. Martina, and M. Shafique, “Is Spiking Secure? A Comparative Study on the Security Vulnerabilities of Spiking and Deep Neural Networks,” in 2020 International Joint Conference on Neural Networks, IJCNN 2020, Glasgow, United Kingdom, July 19-24, 2020, pp. 1–8, IEEE, 2020.

[C11]     V. Venceslai, A. Marchisio, I. Alouani, M. Martina, and M. Shafique, “NeuroAttack: Undermining Spiking Neural Networks Security through Externally Triggered BitFlips,” in 2020 International Joint Conference on Neural Networks, IJCNN 2020, Glasgow, United Kingdom, July 19-24, 2020, pp. 1–8, IEEE, 2020.

[C12]     A. Marchisio, B. Bussolino, A. Colucci, M. A. Hanif, M. Martina, G. Masera, and M. Shafique, “FasTrCaps: An Integrated Framework for Fast yet Accurate Training of Capsule Networks,” in 2020 International Joint Conference on Neural Networks, IJCNN 2020, Glasgow, United Kingdom, July 19-24, 2020, pp. 1–8, IEEE, 2020.

[C13]     A. Viale, A. Marchisio, M. Martina, G. Masera, and M. Shafique, “CarSNN: An Efficient Spiking Neural Network for Event-Based Autonomous Cars on the Loihi Neuromorphic Research Processor,” in 2021 International Joint Conference on Neural Networks, IJCNN 2021, Shenzhen, China, July 18-22, 2021, pp. 1–10, IEEE, 2021.

[C14]     A. Marchisio, G. Pira, M. Martina, G. Masera, and M. Shafique, “DVS-Attacks: Adversarial Attacks on Dynamic Vision Sensors for Spiking Neural Networks,” in 2021 International Joint Conference on Neural Networks, IJCNN 2021, Shenzhen, China, July 18-22, 2021, pp. 1–9, IEEE, 2021.

[C15]     A. Marchisio, G. Caramia, M. Martina, and M. Shafique, “fakeWeather: Adversarial Attacks for Deep Neural Networks Emulating Weather Conditions on the Camera Lens of Autonomous Systems,” in 2022 International Joint Conference on Neural Networks, IJCNN 2022, Padua, Italy, July 18-23, 2022, pp. 1-9, IEEE, 2022.

[C16]     A. Marchisio, A. De Marco, A. Colucci, M. Martina, and M. Shafique, “RobCaps: Evaluating the Robustness of Capsule Networks against Affine Transformations and Adversarial Attacks,” in 2023 International Joint Conference on Neural Networks, IJCNN 2023, Gold Coast, Queensland, Australia, June 18-23, 2023, pp. 1-9, IEEE, 2023.

[C17]     S. Dave, A. Marchisio, M. A. Hanif, A. Guesmi, A. Shrivastava, I. Alouani, and M. Shafique, “Special Session: Towards an Agile Design Methodology for Efficient, Reliable, and Secure ML Systems,” in IEEE VLSI Test Symposium, VTS 2022, Synopsys Inc., CA, USA, April 25-27, 2022, IEEE, 2022.

[C18]     A. Marchisio, M. A. Hanif, F. Khalid, G. Plastiras, C. Kyrkou, T. Theocharides, and M. Shafique, “Deep Learning for Edge Computing: Current Trends, Cross-Layer Optimizations, and Open Research Challenges,” in 2019 IEEE Computer Society Annual Symposium on VLSI, ISVLSI 2019, Miami, FL, USA, July 15-17, 2019, pp. 553–559, IEEE, 2019.

Workshop Publications

[W1]      A. Marchisio, G. Nanfa, F. Khalid, M. A. Hanif, M. Martina, and M. Shafique, “CapsAttacks: Robust and Imperceptible Adversarial Attacks on Capsule Networks,” ICML Workshop on Uncertainty & Robustness in Deep Learning, UDL 2019, Long Beach, CA, USA, July 9-15, 2019.

[W2]      A. Marchisio, V. Mrazek, A. Massa, B. Bussolino, M. Martina, and M. Shafique, “HARNAS: Neural Architecture Search Jointly Optimizing for Hardware Efficiency and Adversarial Robustness of Convolutional and Capsule Networks,” ICML Workshop on Dynamic Neural Networks, DyNN 2022, Baltimore, MD, USA, July 17-23, 2022.

Journal Publications

[J1]        A. Marchisio, V. Mrazek, M. A. Hanif, and M. Shafique, “FEECA: Design Space Exploration for Low-Latency and Energy-Efficient Capsule Network Accelerators,” IEEE Trans. Very Large Scale Integr. Syst. (TVLSI), vol. 29, no. 4, pp. 716–729, 2021.

[J2]        A. Marchisio, V. Mrazek, M. A. Hanif, and M. Shafique, “DESCNet: Developing Efficient Scratchpad Memories for Capsule Network Hardware,” IEEE Trans. Comput. Aided Des. Integr. Circuits Syst. (TCAD), vol. 40, no. 9, pp. 1768–1781, 2021.

[J3]        A. Marchisio, V. Mrazek, A. Massa, B. Bussolino, M. Martina, and M. Shafique, “RoHNAS: A Neural Architecture Search Framework with Conjoint Optimization for Adversarial Robustness and Hardware Efficiency of Convolutional and Capsule Networks,” IEEE Access, vol. 10, pp. 109043–109055, 2022.

[J4]        A. Marchisio, G. Nanfa, F. Khalid, M. A. Hanif, M. Martina, and M. Shafique, “SeVuC: A Study on the Security Vulnerabilities of Capsule Networks against Adversarial Attacks” Microprocessors and Microsystems (MICPRO), vol. 96, pp. 104738, 2023.

Ph. D. Thesis Abstract

Machine Learning (ML) algorithms have shown a high level of accuracy in several tasks. Therefore, ML-based applications are widely used in many systems and platforms. However, developing efficient ML-based systems requires addressing two fundamental research problems: energy-efficiency and robustness. Current trends show the growing interest in the community for complex ML models, such as Deep Neural Networks (DNNs), Capsule Networks (CapsNets), and Spiking Neural Networks (SNNs). Besides their high learning capabilities, their complexity poses several research challenges.

State-of-the-art DNN accelerators typically optimize the execution of the most common layers and operations. Still, they become obsolete when executing more advanced types of ML architectures, such as CapsNets that involve complex operations or SNNs that support a different computational infrastructure known as a neuromorphic system. Moreover, multiple vulnerability aspects threaten the correct functionality of ML systems. Therefore, it is crucial to investigate security-oriented techniques for enhancing the robustness of such advanced ML architectures, which might offer peculiar properties in terms of resiliency in adverse conditions that are different from traditional DNNs. Another critical limitation of state-of-the-art techniques is that they typically focus on optimizing for a single objective or have a limited set of goals.

In this regard, this thesis tackles the above-discussed challenges by exploiting the unique features of advanced ML models and investigates cross-layer concepts and techniques to engage both hardware and software-level methods to build robust and energy-efficient architectures for these advanced ML networks. More specifically, this research improves the energy efficiency of complex models like CapsNets, through a specialized flow of hardware-level designs and software-level optimizations exploiting the application-driven knowledge of these systems and the error tolerance through approximations and quantization. This research also improves the robustness of ML models, in particular for SNNs executed on neuromorphic hardware, due to their inherent cost-effective features. Moreover, this research integrates multiple optimization objectives into specialized frameworks for jointly optimizing the robustness and energy efficiency of these systems.