Pascal Berrang
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…
Guardrail Classifiers defend production language models against harmful behavior, but although results seem promising in testing, they provide no formal guarantees. Providing formal guarantees for such models is hard because "harmful…
We introduce a technology to formally verify that a software system satisfies a temporal specification of functional correctness, without revealing the system itself. Our method combines a deductive approach to model checking to obtain a…
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…
Can you imagine, blockchain transactions can talk! In this paper, we study how they talk and what they talk about. We focus on the input data field of Ethereum transactions, which is designed to allow external callers to interact with smart…
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 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…
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…
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…
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 Decentralized…
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…
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 resources…
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).…
In this paper, we develop a user-centric privacy framework for quantitatively assessing the exposure of personal information in open settings. Our formalization addresses key-challenges posed by such open settings, such as the unstructured…