3 citations · 4 across the 10 of their papers we have counts for
11 papers
ABSENTIA: Detecting Broken Access Control Vulnerabilities in Web Applications
André V. Duarte, Aditya Oke, Rui Melo +7
Broken access control, the failure of authorization, is one of the most prevalent web security risks. Unlike injection, a flow of untrusted input into a dangerous operation, author…
Sem-Detect: Semantic Level Detection of AI Generated Peer-Reviews
André V. Duarte, Brian Tufts, Aditya Oke +3
How can we distinguish whether a peer review was written by a human or generated by an AI model? We argue that, in this setting, authorship should not be attributed solely from the…
RECAP: Reproducing Copyrighted Data from LLMs Training with an Agentic Pipeline
André V. Duarte, Xuying li, Bin Zeng +3
If we cannot inspect the training data of a large language model (LLM), how can we ever know what it has seen? We believe the most compelling evidence arises when the model itself…
Deep Feedback Models
David Calhas, Arlindo L. Oliveira
Deep Feedback Models (DFMs) are a new class of stateful neural networks that combine bottom up input with high level representations over time. This feedback mechanism introduces d…
Deep Recurrence for Dynamical Segmentation Models
David Calhas, Arlindo L. Oliveira
While biological vision systems rely heavily on feedback connections to iteratively refine perception, most artificial neural networks remain purely feedforward, processing input i…
Are ECGs enough? Deep learning classification of pulmonary embolism using electrocardiograms
Joao D. S. Marques, Arlindo L. Oliveira
Pulmonary embolism is a leading cause of out of hospital cardiac arrest that requires fast diagnosis. While computed tomography pulmonary angiography is the standard diagnostic too…
DIS-CO: Discovering Copyrighted Content in VLMs Training Data
André V. Duarte, Xuandong Zhao, Arlindo L. Oliveira +1
How can we verify whether copyrighted content was used to train a large vision-language model (VLM) without direct access to its training data? Motivated by the hypothesis that a V…
The role of positional encodings in the ARC benchmark
Guilherme H. Bandeira Costa, Miguel Freire, Arlindo L. Oliveira
The Abstraction and Reasoning Corpus challenges AI systems to perform abstract reasoning with minimal training data, a task intuitive for humans but demanding for machine learning…
The Role of Recurrency in Image Segmentation for Noisy and Limited Sample Settings
David Calhas, João Marques, Arlindo L. Oliveira
The biological brain has inspired multiple advances in machine learning. However, most state-of-the-art models in computer vision do not operate like the human brain, simply becaus…
LumberChunker: Long-Form Narrative Document Segmentation
André V. Duarte, João Marques, Miguel Graça +3
Modern NLP tasks increasingly rely on dense retrieval methods to access up-to-date and relevant contextual information. We are motivated by the premise that retrieval benefits from…
DE-COP: Detecting Copyrighted Content in Language Models Training Data
André V. Duarte, Xuandong Zhao, Arlindo L. Oliveira +1
How can we detect if copyrighted content was used in the training process of a language model, considering that the training data is typically undisclosed? We are motivated by the…