Pascal Berrang
YOU?
Author Swipe
View article: Evasion Under Blockchain Sanctions
Evasion Under Blockchain Sanctions Open
Sanctioning blockchain addresses has become a common regulatory response to malicious activities. However, enforcement on permissionless blockchains remains challenging due to complex transaction flows and sophisticated fund-obfuscation te…
View article: 3S-Attack: Spatial, Spectral and Semantic Invisible Backdoor Attack Against DNN Models
3S-Attack: Spatial, Spectral and Semantic Invisible Backdoor Attack Against DNN Models Open
Backdoor attacks implant hidden behaviors into models by poisoning training data or modifying the model directly. These attacks aim to maintain high accuracy on benign inputs while causing misclassification when a specific trigger is prese…
View article: SoK: Descriptive Statistics Under Local Differential Privacy
SoK: Descriptive Statistics Under Local Differential Privacy Open
Local Differential Privacy (LDP) provides a formal guarantee of privacy that enables the collection and analysis of sensitive data without revealing any individual's data. While LDP methods have been extensively studied, there is a lack of…
View article: Measuring Conditional Anonymity - A Global Study
Measuring Conditional Anonymity - A Global Study Open
The realm of digital health is experiencing a global surge, with mobile applications extending their reach into various facets of daily life. From tracking daily eating habits and vital functions to monitoring sleep patterns and even the m…
View article: Link Stealing Attacks Against Inductive Graph Neural Networks
Link Stealing Attacks Against Inductive Graph Neural Networks Open
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, including the transductive setting and the inductive setting. In t…
View article: Link Stealing Attacks Against Inductive Graph Neural Networks
Link Stealing Attacks Against Inductive Graph Neural Networks Open
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, including the transductive setting and the inductive setting. In t…
View article: Quantifying Privacy Risks of Prompts in Visual Prompt Learning
Quantifying Privacy Risks of Prompts in Visual Prompt Learning Open
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 update the pre-trained model's parameters. Instead, it only lea…
View article: Accountable Javascript Code Delivery
Accountable Javascript Code Delivery Open
The Internet is a major distribution platform for web applications, but there are no effective transparency and audit mechanisms in place for the web. Due to the ephemeral nature of web applications, a client visiting a website has no guar…
View article: Accountable Javascript Code Delivery
Accountable Javascript Code Delivery Open
The Internet is a major distribution platform for web applications, but there are no effective transparency and audit mechanisms in place for the web. Due to the ephemeral nature of web applications, a client visiting a website has no guar…
View article: Fine-Tuning Is All You Need to Mitigate Backdoor Attacks
Fine-Tuning Is All You Need to Mitigate Backdoor Attacks Open
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 increasingly complex and often require high computational resource…
View article: Data Poisoning Attacks Against Multimodal Encoders
Data Poisoning Attacks Against Multimodal Encoders Open
Recently, the newly emerged multimodal models, which leverage both visual and linguistic modalities to train powerful encoders, have gained increasing attention. However, learning from a large-scale unlabeled dataset also exposes the model…
View article: On How Zero-Knowledge Proof Blockchain Mixers Improve, and Worsen User Privacy
On How Zero-Knowledge Proof Blockchain Mixers Improve, and Worsen User Privacy Open
Zero-knowledge proof (ZKP) mixers are one of the most widely-used blockchain privacy solutions, operating on top of smart contract-enabled blockchains. We find that ZKP mixers are tightly intertwined with the growing number of Decentralize…
View article: Membership Inference Against DNA Methylation Databases
Membership Inference Against DNA Methylation Databases Open
Biomedical data sharing is one of the key elements fostering the advancement of biomedical research but poses severe risks towards the privacy of individuals contributing their data, as already demonstrated for genomic data. In this paper,…
View article: Albatross: An optimistic consensus algorithm
Albatross: An optimistic consensus algorithm Open
The consensus protocol is a critical component of distributed ledgers and blockchains. Achieving consensus over a decentralized network poses challenges to transaction finality and performance. Currently, the highest-performing consensus a…
View article: Albatross: An optimistic consensus algorithm
Albatross: An optimistic consensus algorithm Open
The area of distributed ledgers is a vast and quickly developing landscape. At the heart of most distributed ledgers is their consensus protocol. The consensus protocol describes the way participants in a distributed network interact with …
View article: MBeacon: Privacy-Preserving Beacons for DNA Methylation Data
MBeacon: Privacy-Preserving Beacons for DNA Methylation Data Open
The advancement of molecular profiling techniques fuels biomedical research with a deluge of data. To facilitate data sharing, the Global Alliance for Genomics and Health established the Beacon system, a search engine designed to help rese…
View article: ML-Leaks: Model and Data Independent Membership Inference Attacks and Defenses on Machine Learning Models
ML-Leaks: Model and Data Independent Membership Inference Attacks and Defenses on Machine Learning Models Open
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 companies to deploy machine learning as a service (MLaaS).…
View article: Privacy-Preserving Similar Patient Queries for Combined Biomedical Data
Privacy-Preserving Similar Patient Queries for Combined Biomedical Data Open
The decreasing costs of molecular profiling have fueled the biomedical research community with a plethora of new types of biomedical data, enabling a breakthrough towards more precise and personalized medicine. Naturally, the increasing av…
View article: Simulating the Large-Scale Erosion of Genomic Privacy Over Time
Simulating the Large-Scale Erosion of Genomic Privacy Over Time Open
The dramatically decreasing costs of DNA sequencing have triggered more than a million humans to have their genotypes sequenced. Moreover, these individuals increasingly make their genomic data publicly available, thereby creating privacy …
View article: Dissecting Privacy Risks in Biomedical Data
Dissecting Privacy Risks in Biomedical Data Open
The decreasing costs of molecular profiling has fueled the biomedical research community with a plethora of new types of biomedical data, enabling a breakthrough towards a more precise and personalized medicine. However, the release of the…
View article: Quantifying and mitigating privacy risks in biomedical data
Quantifying and mitigating privacy risks in biomedical data Open
Die stetig sinkenden Kosten für molekulares Profiling haben der Biomedizin zahlreiche neue Arten biomedizinischer Daten geliefert und den Durchbruch für eine präzisere und personalisierte Medizin ermöglicht. Die Veröffentlichung dieser inh…