Related papers: Injection Attacks Against End-to-End Encrypted App…

Backdoor attacks have become an emerging threat to NLP systems. By providing poisoned training data, the adversary can embed a "backdoor" into the victim model, which allows input instances satisfying certain textual patterns (e.g.,…

We show that end-to-end learning of communication systems through deep neural network (DNN) autoencoders can be extremely vulnerable to physical adversarial attacks. Specifically, we elaborate how an attacker can craft effective physical…

Set-based state estimation provides guaranteed state inclusion certificates that are crucial for the safety verification of dynamical systems. However, when system sensors are subject to cyberattacks, maintaining both safety and security…

With over 3 billion users globally, mobile instant messaging apps have become indispensable for both personal and professional communication. Besides plain messaging, many services implement additional features such as delivery and read…

Session is an open-source, public-key-based secure messaging application which uses a set of decentralised storage servers and an onion routing protocol to send end-to-end encrypted messages with minimal exposure of user metadata. It does…

Embeddings have become a cornerstone in the functionality of large language models (LLMs) due to their ability to transform text data into rich, dense numerical representations that capture semantic and syntactic properties. These embedding…

Android is the most widely deployed end-user focused operating system. With its growing set of use cases encompassing communication, navigation, media consumption, entertainment, finance, health, and access to sensors, actuators, cameras,…

Gradient inversion attacks pose significant privacy threats to distributed training frameworks such as federated learning, enabling malicious parties to reconstruct sensitive local training data from gradient communications between clients…

In recent years, many efforts have demonstrated that modern machine learning algorithms are vulnerable to adversarial attacks, where small, but carefully crafted, perturbations on the input can make them fail. While these attack methods are…

Software weaknesses that create attack surfaces for adversarial exploits, such as lateral SQL injection (LSQLi) attacks, are usually introduced during the design phase of software development. Security design patterns are sometimes applied…

Recent studies have revealed a security threat to natural language processing (NLP) models, called the Backdoor Attack. Victim models can maintain competitive performance on clean samples while behaving abnormally on samples with a specific…

Data for deep learning should be protected for privacy preserving. Researchers have come up with the notion of learnable image encryption to satisfy the requirement. However, existing privacy preserving approaches have never considered the…

Backdoor Malware are installed by an attacker on the victim's server(s) for authorized access. A customized backdoor is weaponized to execute unauthorized system, database and application commands to access the user credentials and…

Recent advancements in speech synthesis technology have enriched our daily lives, with high-quality and human-like audio widely adopted across real-world applications. However, malicious exploitation like voice-cloning fraud poses severe…

Privacy concerns have led to the development of privacy-preserving approaches for learning models from sensitive data. Yet, in practice, even models learned with privacy guarantees can inadvertently memorize unique training examples or leak…

For nearly a decade the academic community has investigated backdoors in neural networks, primarily focusing on classification tasks where adversaries manipulate the model prediction. While demonstrably malicious, the immediate real-world…

Microservice architecture gains momentum by fueling systems with cloud-native benefits, scalability, and decentralized evolution. However, new challenges emerge for end-to-end (E2E) testing. Testers who see the decentralized system through…

In this paper, we introduce a data capsule model, a self-contained and self-enforcing data container based on emerging self-sovereign identity standards, blockchain, and attribute-based encryption. A data capsule allows for a transparent,…

Using cloud-based applications comes with privacy implications, as the end-user looses control over their data. While encrypting all data on the client is possible, it largely reduces the usefulness of database management systems (DBMS)…

Post-quantum cryptography studies the security of classical, i.e. non-quantum cryptographic protocols against quantum attacks. Until recently, the considered adversaries were assumed to use quantum computers and behave like classical…