Related papers: Injection Attacks Against End-to-End Encrypted App…
The Long Term Evolution of UMTS is one of the latest steps in an advancing series of mobile telecommunications systems. Many articles have already been published on the LTE subject but these publications have viewed the subject from…
Kintsugi is a protocol for key recovery, allowing a user to regain access to end-to-end encrypted data after they have lost their device, but still have their (potentially low-entropy) password. Existing E2EE key recovery methods, such as…
Privacy concerns have become increasingly critical in modern AI and data science applications, where sensitive information is collected, analyzed, and shared across diverse domains such as healthcare, finance, and mobility. While prior…
Recent works investigated attacks on sensors by influencing analog sensor components with acoustic, light, and electromagnetic signals. Such attacks can have extensive security, reliability, and safety implications since many types of the…
Maintaining the security of control systems in the presence of integrity attacks is a significant challenge. In literature, several possible attacks against control systems have been formulated including replay, false data injection, and…
Fully Homomorphic Encryption (FHE) is seeing increasing real-world deployment to protect data in use by allowing computation over encrypted data. However, the same malleability that enables homomorphic computations also raises integrity…
With the emergence of low-cost smart and connected IoT devices, the area of cyber-physical security is becoming increasingly important. Past research has demonstrated new threat vectors targeting the transition process between the cyber and…
The notion that collaborative machine learning can ensure privacy by just withholding the raw data is widely acknowledged to be flawed. Over the past seven years, the literature has revealed several privacy attacks that enable adversaries…
Malware remains a big threat to cyber security, calling for machine learning based malware detection. While promising, such detectors are known to be vulnerable to evasion attacks. Ensemble learning typically facilitates countermeasures,…
We consider an echo-assisted communication model wherein block-coded messages, when transmitted across several frames, reach the destination as multiple noisy copies. We address adversarial attacks on such models wherein a subset of the…
Mobile instant messengers such as WhatsApp use delivery status notifications in order to inform users if a sent message has successfully reached its destination. This is useful and important information for the sender due to the often…
In big data systems, the infrastructure is such that large amounts of data are hosted away from the users. In such a system information security is considered as a major challenge. From a customer perspective, one of the big risks in…
Mobile applications (apps) have become deeply personal, constantly demanding access to privacy-sensitive information in exchange for more personalized user experiences. Such privacy-invading practices have generated major multidimensional…
As an emerging technique for confidential computing, trusted execution environment (TEE) receives a lot of attention. To better develop, deploy, and run secure applications on a TEE platform such as Intel's SGX, both academic and industrial…
Despite the linearity of its encoding, compressed sensing may be used to provide a limited form of data protection when random encoding matrices are used to produce sets of low-dimensional measurements (ciphertexts). In this paper we…
Pre-trained encoders available online have been widely adopted to build downstream machine learning (ML) services, but various attacks against these encoders also post security and privacy threats toward such a downstream ML service…
Recently, self-supervised learning (SSL) was shown to be vulnerable to patch-based data poisoning backdoor attacks. It was shown that an adversary can poison a small part of the unlabeled data so that when a victim trains an SSL model on…
Semantic communication systems, which leverage Generative AI (GAI) to transmit semantic meaning rather than raw data, are poised to revolutionize modern communications. However, they are vulnerable to backdoor attacks, a type of poisoning…
Growing concern for individual privacy, driven by an increased public awareness of the degree to which many of our electronic activities are tracked by interested third parties (e.g. Google knows what I am thinking before I finish entering…
To promote secure and private artificial intelligence (SPAI), we review studies on the model security and data privacy of DNNs. Model security allows system to behave as intended without being affected by malicious external influences that…