37 citations · 224 across the 83 of their papers we have counts for
18 papers · 1 filter
MIMIR: Masked Image Modeling for Mutual Information-based Adversarial Robustness
Xiaoyun Xu, Shujian Yu, Zhuoran Liu +1
Vision Transformers (ViTs) have emerged as a fundamental architecture and serve as the backbone of modern vision-language models. Despite their impressive performance, ViTs exhibit…
Dr. Jekyll and Mr. Hyde: Two Faces of LLMs
Matteo Gioele Collu, Tom Janssen-Groesbeek, Stefanos Koffas +2
Large Language Models (LLMs) are being integrated into applications such as chatbots or email assistants. To prevent improper responses, safety mechanisms, such as Reinforcement Le…
Look into the Mirror: Evolving Self-Dual Bent Boolean Functions
Claude Carlet, Marko Ðurasevic, Domagoj Jakobovic +2
Bent Boolean functions are important objects in cryptography and coding theory, and there are several general approaches for constructing such functions. Metaheuristics proved to b…
A New Angle: On Evolving Rotation Symmetric Boolean Functions
Claude Carlet, Marko Ðurasevic, Bruno Gašperov +3
Rotation symmetric Boolean functions represent an interesting class of Boolean functions as they are relatively rare compared to general Boolean functions. At the same time, the fu…
Backdoor Attacks on Transformers for Tabular Data: An Empirical Study
Bart Pleiter, Behrad Tajalli, Stefanos Koffas +4
Deep Neural Networks (DNNs) have shown great promise in various domains. However, vulnerabilities associated with DNN training, such as backdoor attacks, are a significant concern.…
Momentum Gradient-based Untargeted Attack on Hypergraph Neural Networks
Yang Chen, Stjepan Picek, Zhonglin Ye +2
Hypergraph Neural Networks (HGNNs) have been successfully applied in various hypergraph-related tasks due to their excellent higher-order representation capabilities. Recent works…
Invisible Threats: Backdoor Attack in OCR Systems
Mauro Conti, Nicola Farronato, Stefanos Koffas +2
Optical Character Recognition (OCR) is a widely used tool to extract text from scanned documents. Today, the state-of-the-art is achieved by exploiting deep neural networks. Howeve…
Label Inference Attacks against Node-level Vertical Federated GNNs
Marco Arazzi, Mauro Conti, Stefanos Koffas +4
Federated learning enables collaborative training of machine learning models by keeping the raw data of the involved workers private. Three of its main objectives are to improve th…
FLAIRS: FPGA-Accelerated Inference-Resistant & Secure Federated Learning
Huimin Li, Phillip Rieger, Shaza Zeitouni +2
Federated Learning (FL) has become very popular since it enables clients to train a joint model collaboratively without sharing their private data. However, FL has been shown to be…
Turning Privacy-preserving Mechanisms against Federated Learning
Marco Arazzi, Mauro Conti, Antonino Nocera +1
Recently, researchers have successfully employed Graph Neural Networks (GNNs) to build enhanced recommender systems due to their capability to learn patterns from the interaction b…
Rethinking the Trigger-injecting Position in Graph Backdoor Attack
Jing Xu, Gorka Abad, Stjepan Picek
Backdoor attacks have been demonstrated as a security threat for machine learning models. Traditional backdoor attacks intend to inject backdoor functionality into the model such t…
Digging Deeper: Operator Analysis for Optimizing Nonlinearity of Boolean Functions
Marko Djurasevic, Domagoj Jakobovic, Luca Mariot +1
Boolean functions are mathematical objects with numerous applications in domains like coding theory, cryptography, and telecommunications. Finding Boolean functions with specific p…
IB-RAR: Information Bottleneck as Regularizer for Adversarial Robustness
Xiaoyun Xu, Guilherme Perin, Stjepan Picek
In this paper, we propose a novel method, IB-RAR, which uses Information Bottleneck (IB) to strengthen adversarial robustness for both adversarial training and non-adversarial-trai…
On Feasibility of Server-side Backdoor Attacks on Split Learning
Behrad Tajalli, Oguzhan Ersoy, Stjepan Picek
Split learning is a collaborative learning design that allows several participants (clients) to train a shared model while keeping their datasets private. Recent studies demonstrat…
Sneaky Spikes: Uncovering Stealthy Backdoor Attacks in Spiking Neural Networks with Neuromorphic Data
Gorka Abad, Oguzhan Ersoy, Stjepan Picek +1
Deep neural networks (DNNs) have demonstrated remarkable performance across various tasks, including image and speech recognition. However, maximizing the effectiveness of DNNs req…
SoK: A Systematic Evaluation of Backdoor Trigger Characteristics in Image Classification
Gorka Abad, Jing Xu, Stefanos Koffas +3
Deep learning achieves outstanding results in many machine learning tasks. Nevertheless, it is vulnerable to backdoor attacks that modify the training set to embed a secret functio…
Universal Soldier: Using Universal Adversarial Perturbations for Detecting Backdoor Attacks
Xiaoyun Xu, Oguzhan Ersoy, Stjepan Picek
Deep learning models achieve excellent performance in numerous machine learning tasks. Yet, they suffer from security-related issues such as adversarial examples and poisoning (bac…
A Survey of Metaheuristic Algorithms for the Design of Cryptographic Boolean Functions
Marko Djurasevic, Domagoj Jakobovic, Luca Mariot +1
Boolean functions are mathematical objects used in diverse domains and have been actively researched for several decades already. One domain where Boolean functions play an importa…