Positions: 3
Research Grant (BI)
BI|2026/880 Projet SALVE – refª 2024.14936.PEX
Type of position: Research Grant (BI)
Duration: 5 months
Deadline to apply: 4216-05-30
DescriptionONE (1) research grant for students with BSc degree with reference number BI|2026/880 under the scope of the Projet SALVE: Securing Artificial Language Models Against Vulnerability Encoding (2024.14936.PEX), funded by Fundação para a Ciência e a Tecnologia, is available under the following conditions:
OBJECTIVES | FUNCTIONS
This task evaluates the impact of controlled code perturbations on the classification stability and robustness of Large Language Models (LLMs) in distinguishing secure from insecure JavaScript code. The student will design and implement a systematic evaluation pipeline to assess model behavior under perturbation-induced variations. The work plan includes:
Evaluation Pipeline Development (Month 1) Implement a scalable evaluation framework using local LLM infrastructure (e.g., Ollama, LMStudio). Integrate multiple LLMs for comparative evaluation. Automate classification experiments across original and perturbed datasets. Classification Shift Analysis (Month 2) Measure classification changes between original and perturbed code variants. Identify perturbations that cause label flips (secure ↔ insecure).Quantify: Misclassification rate, Stability rate, False positive rate, False negative rate
Robustness Assessment (Month 3-4) Define robustness metrics for security classification consistency. Evaluate resilience to obfuscation, control-flow changes, and API variations.Compare robustness performance across different models.
Misclassification Characterization (Month 4-5) Construct an augmented misclassification dataset containing: original and perturbed variants, model predictions, correct labels, perturbation typeAnalyze patterns in failure cases.
Exploratory Explainability Analysis (Optional) Investigate whether explainability tools can help identify model reliance on superficial features. Analyze whether models rely on syntax-level heuristics versus security-relevant semantics.All experimental artifacts, code, and results will be released in an open-source repository. The selected candidate will be integrated into a research team with established expertise in software security, program analysis, and AI-driven code intelligence, with a track record of collaboration with leading technology companies and publications in top-tier international conferences and journals.
Contact email: bolsas@inesc-id.ptBI|2026/882 Projet SALVE – refª 2024.14936.PEX
Type of position: Research Grant (BI)
Duration: 6 months
Deadline to apply: 2026-12-31
DescriptionONE (1) research grant for students with BSc degree with reference number BI|2026/882 under the scope of the Projet SALVE: Securing Artificial Language Models Against Vulnerability Encoding (2024.14936.PEX), funded by Fundação para a Ciência e a Tecnologia, is available under the following conditions:
OBJECTIVES | FUNCTIONS
This task aims to develop an automated and scalable framework for the continuous improvement of security-aware Large Language Models (LLMs), integrating dataset expansion, evaluation, incremental fine-tuning, and security-aware code generation validation. The student will build an integrated pipeline that reuses artifacts developed in previous tasks and ensures systematic model improvement over time. The work plan includes:
Automated Dataset Expansion (Month 1) Implement mechanisms to collect and track secure and insecure JavaScript code from open-source repositories. Identify and label security-related commits using diff-based analysis. Integrate synthetic data generation (e.g., AST-based vulnerability injection) to increase dataset diversity. Continuous Model Evaluation (Month 2) Implement automated evaluation of security classification performance on expanded datasets. Measure classification accuracy, precision, recall, and robustness over time. Track performance differentials across evaluation cycles. Incremental Fine-Tuning and Feedback Integration (Month 3) Implement periodic fine-tuning of selected models using curated secure–insecure code pairs. Integrate adaptive feedback mechanisms based on misclassification analysis. Ensure reproducibility and version control of model updates. Security-Aware Code Generation Testing (Month 4) Integrate static analysis tools (e.g., Semgrep, CodeQL) to assess generated code. Measure vulnerability density (e.g., vulnerabilities per 100 lines of code). Compare improvements across pipeline iterations. Validation and Framework Assessment (Month 5-6) Conduct two full validation cycles in the final four months. Measure improvements in: Security classification accuracy Robustness to adversarial modifications Reduction of AI-generated vulnerabilitiesAll artifacts will be released as open-source and documented for reproducibility. The selected candidate will be integrated into a research team with established expertise in software security, program analysis, and AI-driven code intelligence, with a track record of collaboration with leading technology companies and publications in top-tier international conferences and journals.
Contact email: bolsas@inesc-id.ptBI|2026/962-MALDIBANK Refª 101188201
Type of position: Research Grant (BI)
Duration: 5 months
Deadline to apply: 2026-11-09
DescriptionONE (1) research grant for students enrolled in a Master degree in Biomedical Engineering or related areas, with the reference number BI|2026/962 under the scope of the Project MALDIBANK with the Refª 101188201, funded by European Commission, program Horizon Europe, is available under the following conditions:
OBJECTIVES | FUNCTIONS
Establish a biobank integrating imaging data and unstructured reports. The platform will be designed around critical functional requirements and quality attributes, providing frontend interfaces, analytical capabilities, 3D volumetric image segmentation, and multimodal querying to support efficient data retrieval and exploration.
Step 1 — Requirements and Architecture: define functional requirements, quality attributes, FAIR principles, data governance, interoperability standards, and the target system architecture.
Step 2 — Data Integration: Develop the data infrastructure to ingest, harmonize, index, and consolidate all data sources, ensuring secure access and metadata traceability.
Step 3 — Frontend and Analytical Capabilities: Implement APIs, interactive 3D image visualization, volumetric segmentation workflows, and multimodal search and query capabilities.
Step 4 — Validation: Validate data quality, FAIR compliance, usability, security, and system performance; evaluate segmentation and query accuracy.
Contact email: bolsas@inesc-id.pt