Publications (21)
Fine-Tuning Is All You Need to Mitigate Backdoor Attacks
Zeyang Sha, Xinlei He, Pascal Berrang +2
Backdoor attacks represent one of the major threats to machine learning models. Various efforts have been made to mitigate backdoors. However, existing defenses have become increas…
Data Poisoning Attacks Against Multimodal Encoders
Ziqing Yang, Xinlei He, Zheng Li +4
Recently, the newly emerged multimodal models, which leverage both visual and linguistic modalities to train powerful encoders, have gained increasing attention. However, learning…
Quantifying Privacy Risks of Prompts in Visual Prompt Learning
Yixin Wu, Rui Wen, Michael Backes +4
Large-scale pre-trained models are increasingly adapted to downstream tasks through a new paradigm called prompt learning. In contrast to fine-tuning, prompt learning does not upda…
Shorts vs. Regular Videos on YouTube: A Comparative Analysis of User Engagement and Content Creation Trends
Caroline Violot, TuÄrulcan Elmas, Igor Bilogrevic +1
YouTube introduced the Shorts video format in 2021, allowing users to upload short videos that are prominently displayed on its website and app. Despite having such a large visual…
On (The Lack Of) Location Privacy in Crowdsourcing Applications
Spyros Boukoros, Mathias Humbert, Stefan Katzenbeisser +1
Crowdsourcing enables application developers to benefit from large and diverse datasets at a low cost. Specifically, mobile crowdsourcing (MCS) leverages users' devices as sensors…
In Times of Crisis: An Exploratory Study of Media and Political Discourse on YouTube During the 2024 French Elections
Vera Sosnovik, Caroline Violot, Mathias Humbert
YouTube has emerged as a major platform for political communication and news dissemination, particularly during high-stakes electoral periods. In the context of the 2024 European P…
Image Obfuscation for Privacy-Preserving Machine Learning
Mathilde Raynal, Radhakrishna Achanta, Mathias Humbert
Privacy becomes a crucial issue when outsourcing the training of machine learning (ML) models to cloud-based platforms offering machine-learning services. While solutions based on…
FairTest: Discovering Unwarranted Associations in Data-Driven Applications
Florian Tramèr, Vaggelis Atlidakis, Roxana Geambasu +5
In a world where traditional notions of privacy are increasingly challenged by the myriad companies that collect and analyze our data, it is important that decision-making entities…
BAAAN: Backdoor Attacks Against Autoencoder and GAN-Based Machine Learning Models
Ahmed Salem, Yannick Sautter, Michael Backes +2
The tremendous progress of autoencoders and generative adversarial networks (GANs) has led to their application to multiple critical tasks, such as fraud detection and sanitized da…
ML-Leaks: Model and Data Independent Membership Inference Attacks and Defenses on Machine Learning Models
Ahmed Salem, Yang Zhang, Mathias Humbert +3
Machine learning (ML) has become a core component of many real-world applications and training data is a key factor that drives current progress. This huge success has led Internet…
Towards Plausible Graph Anonymization
Yang Zhang, Mathias Humbert, Bartlomiej Surma +3
Social graphs derived from online social interactions contain a wealth of information that is nowadays extensively used by both industry and academia. However, as social graphs con…
When Machine Unlearning Jeopardizes Privacy
Min Chen, Zhikun Zhang, Tianhao Wang +3
The right to be forgotten states that a data owner has the right to erase their data from an entity storing it. In the context of machine learning (ML), the right to be forgotten r…
Exploring YouTube's Political Communication Networks during the 2024 French Elections
Caroline Violot, Vera Sosnovik, Mathias Humbert
In 2024, France was shaken by the far-right National Rally's victory in the European elections. In response to this unprecedented result, French President Emmanuel Macron dissolved…
Graph Unlearning
Min Chen, Zhikun Zhang, Tianhao Wang +3
Machine unlearning is a process of removing the impact of some training data from the machine learning (ML) models upon receiving removal requests. While straightforward and legiti…
Towards Mass Adoption of Contact Tracing Apps -- Learning from Users' Preferences to Improve App Design
Dana Naous, Manus Bonner, Mathias Humbert +1
Contact tracing apps have become one of the main approaches to control and slow down the spread of COVID-19 and ease up lockdown measures. While these apps can be very effective in…
Tagvisor: A Privacy Advisor for Sharing Hashtags
Yang Zhang, Mathias Humbert, Tahleen Rahman +3
Hashtag has emerged as a widely used concept of popular culture and campaigns, but its implications on people's privacy have not been investigated so far. In this paper, we present…
Measuring the performance of investments in information security startups: An empirical analysis by cybersecurity sectors using Crunchbase data
Loïc Maréchal, Alain Mermoud, Dimitri Percia David +1
Early-stage firms play a significant role in driving innovation and creating new products and services, especially for cybersecurity. Therefore, evaluating their performance is cru…
Prioritizing Investments in Cybersecurity: Empirical Evidence from an Event Study on the Determinants of Cyberattack Costs
Daniel Celeny, Loïc Maréchal, Evgueni Rousselot +2
Along with the increasing frequency and severity of cyber incidents, understanding their economic implications is paramount. In this context, listed firms' reactions to cyber incid…
Link Stealing Attacks Against Inductive Graph Neural Networks
Yixin Wu, Xinlei He, Pascal Berrang +4
A graph neural network (GNN) is a type of neural network that is specifically designed to process graph-structured data. Typically, GNNs can be implemented in two settings, includi…
walk2friends: Inferring Social Links from Mobility Profiles
Michael Backes, Mathias Humbert, Jun Pang +1
The development of positioning technologies has resulted in an increasing amount of mobility data being available. While bringing a lot of convenience to people's life, such availa…
Contact Tracing: An Overview of Technologies and Cyber Risks
Franck Legendre, Mathias Humbert, Alain Mermoud +1
The 2020 COVID-19 pandemic has led to a global lockdown with severe health and economical consequences. As a result, authorities around the globe have expressed their needs for bet…