External Projects

DÏoT

An autonomous and Distributed Deep Learning Intrusion Detection System for Internet of Things (IoT)

Learn more

HYDRANOS

HYDRANOS aims to revolutionize computing system security with an integrated, full-stack approach that addresses diverse cross-layer attacks. By integrating reconfiguration capabilities into the underlying System-on-Chip (SoC), it enables post-silicon hardware updating and patching, establishing a holistic framework for enhanced hardware-assisted security and more robust computing systems.

Learn more

CROSSING

CROSSING provides cryptography-based security solutions for new and next-generation computing environments, ensuring efficiency, robustness, and ease of use for developers, administrators, and end users, regardless of their expertise in cryptography.

Learn more

ACES

ACES focuses on researching and developing an open ML-enabled architecture to meet the growing demand for cloud services at the edge. The project ensures end-to-end transaction resilience, reliability, and stable automation in cloud management, while also maintaining secure flows of sensitive data and applications.

Learn more

IoTGuard

In IoTGuard, we develope a novel distributed AI-based detection methods against attacks on IoT systems.

Learn more

CROSSCON

CROSSCON aims to create an open-source security stack for IoT, providing secure applications across diverse devices and architectures. It focuses on enhancing memory protection, isolating Trusted Execution Environments, and offering high-assurance trusted services with a lightweight security toolchain.

Learn more

Internal Projects

  • Distribute ML: We are exploring the security and privacy dimensions of distributed machine learning. Specifically, we are developing novel attacks and defenses in prominent areas like Federated Learning and Split Learning. We aim to contribute valuable insights that enhance the robustness and resilience of distributed machine learning systems. Our focus encompasses the identification and mitigation of potential vulnerabilities, ensuring the confidentiality and integrity of data and models in these collaborative learning frameworks.
  • Hardware Fuzzing: Fuzzing's success in finding software vulnerabilities has led to its consideration for hardware security testing. Adapting software fuzzers for hardware faces challenges due to architectural differences. Our research focuses on creating an advanced hardware fuzzer for processors and SoCs. It employs information flow tracking and machine learning techniques to generate impactful test cases, offer detailed feedback, and identify subtle vulnerabilities such as information leaks.
  • ML and Physics Principles: Doppler Effects, Conservation of Energy, Conservation of Momentum or the Laws of Thermodynamics can be used to improve the results of some Artificial Intelligence neural networks? To answer this question, we are investigating the impact of this principles for XAI, text-detection or attacks defences.
  • Watermarking: NN training is a very expensive task, that consts companies billions of dollars to perform. To protect the intellectual property, it is possible to inject a watermarking inside the weights of the model (white-box) or on the output (black-box). We investigate how to inject and remove a watermark inside the model without losing accuracy.
  • GNN:We are currently investigating the use of Graph Neural Networks for Anomaly Detection and Hardware Fuzzing to improve the performances and speed up the process of those two tasks.
  • IoT: We take care of authentication, communication and more, everything with a special eye on security. We propose hands on projects, with PCB and IoT devices but we also analyse the security of IoT devices with Artificial Intelligence.
  • DeepFake Attacks and Protection: DeepFake and DeepFake Detector become more prevalent by the day. The creation of fake news is dangerous by virtue of making people confuse what’s true and what’s not. To combat this, we are currently investigating DeepFake to create attacks and countermeasures against it.