Positions: 5
Research Grant (BI)
Refª BI|2025/638 - PRELUNA – refª refª PTDC/CCI-INF/4703/202
Type of position: Research Grant (BI)
Duration: 4 months
Deadline to apply: 2025-01-31
DescriptionCreate robust machine learning models for vision inspired in the structure and behavior of the central nervous system, in particular in the first layers of the ventral stream in primates. The objective is to modify existing standard backbones based on CNNs to include layers of biologically inspired units leading to architectures more robust to noise and adversarial attacks.
Contact email: bolsas@inesc-id.ptRefª BI|2025/642-Project DIXcover (I3PR009045)
Type of position: Research Grant (BI)
Duration: 6 months
Deadline to apply: 2025-01-29
DescriptionDevelopment of deep-learning models for dual-process computation
The objective of the work is the design and analysis of deep neural network architectures inspired in dual process computation mechanisms that are able to reason and solve problems outside the reach of existing vision and language models. While existing deep learning models execute tasks like face and object recognition and natural languagem processing, which are executed effortlessly by the human brain, they still perform poorly in tasks that require reasoning and conscious effort, like answering complex riddles, executing non-trivial arithmetic operations or planning unfamiliar tasks. The objective of this work is to study and develop deep learning architectures that can excel in both types of tasks.
Contact email: bolsas@inesc-id.ptRefª BI|2025/641-Project DIXcover (I3PR009045)
Type of position: Research Grant (BI)
Duration: 6 months
Deadline to apply: 2025-01-29
DescriptionDevelopment of biologically inspired deep learning models for image analisys
Create robust machine learning models for vision inspired by the structure and behavior of the central nervous system, in particular in the first layers of the areas in the ventral stream of primates. The objective is to modify existing standard backbones based on convolutional neural networks to include layers of biologically inspired units leading to architectures more robust to noise and adversarial attacks.
Contact email: bolsas@inesc-id.ptBI|2025/640-SmartRetail – Refª C6632206063-00466847
Type of position: Research Grant (BI)
Duration: 10 months
Deadline to apply: 2025-01-28
DescriptionReal-time Privacy-preserving Systems for Smart-Retail Stores
The goal of this project is to contribute to the development of advanced security and privacy-preserving technologies for smart-retail stores. Specifically, this project aims to explore new techniques that can protect customers' privacy in smart-retail transactions in real time. First, it will be necessary to perform an extensive analysis of existing systems for processing privacy-sensitive data in real-time and analyze their performance and security properties. Second, based on this analysis, design and implement a prototype of a real-time system aimed at protecting the privacy of smart retail customers when performing transactions and acquiring goods. The expected outcome of this project includes both a report of the analyzed solutions and a software prototype of the implemented solution.
Contact email: bolsas@inesc-id.ptSmartRetail – Refª C6632206063-00466847 - BI|2025/639
Type of position: Research Grant (BI)
Duration: 10 months
Deadline to apply: 2025-01-28
DescriptionDetection of Denial-of-Wallet Vulnerabilities in Cloud-hosted Smart Retail Services
The goal of this project is to contribute to the development of advanced security and privacy-preserving technologies for smart-retail stores. Specifically, this project aims to study an emerging class of vulnerabilities named Denial of Wallet (DoW) attacks. In this type of attack, attackers can exploit vulnerabilities in cloud-hosted services that can trigger excessive resource usage, such as external APIs or public storage, resulting in financial damage to smart retail actors that rely on the cloud for hosting their web applications. Considering these attacks, this project has the following main: (1) Design and implement DoWGuard, a novel detection tool for DoW vulnerabilities in cloud applications; (2) Extend the existing static analysis techniques to include the ability to reason about economic sinks and interactions with cloud APIs. (3) Define and specify queries within DoWGuard to accurately identify DoW vulnerability patterns. (4) Integrate DoWGuard into the CI/CD toolchain, providing developers with immediate feedback on potential DoW vulnerabilities during the development lifecycle. (5) Evaluate DoWGuard's effectiveness by applying it to real-world cloud applications. The expected outcome of this project includes both a report of the analyzed solutions and a software prototype of the implemented solution.
Contact email: bolsas@inesc-id.pt