Related papers: On the Practical Feasibility of Harvest-Now, Decry…

As large language models (LLMs) grow more capable, they face growing vulnerability to sophisticated jailbreak attacks. While developers invest heavily in alignment finetuning and safety guardrails, researchers continue publishing novel…

Homomorphic encryption (HE) applied to a networked controller enables secure operation, but in most cases it allows for addition and multiplication over integers only, because of computation efficiency. Several related results deal with…

This paper will discuss the Logjam attack on TLS. The Logjam attack allows, under certain conditions, to defeat the security provided by TLS. This is done by manipulating server and client into using weak and deprecated export grade crypto,…

In this paper we consider a defending problem on a network. In the model, the defender holds a total defending resource of R, which can be distributed to the nodes of the network. The defending resource allocated to a node can be shared by…

Deep learning (DL) approaches are achieving extraordinary results in a wide range of domains, but often require a massive collection of private data. Hence, methods for training neural networks on the joint data of different data owners,…

We consider the problem of defending a hash table against a Byzantine attacker that is trying to degrade the performance of query, insertion and deletion operations. Our defense makes use of resource burning (RB) -- the the verifiable…

The ever-growing big data and emerging artificial intelligence (AI) demand the use of machine learning (ML) and deep learning (DL) methods. Cybersecurity also benefits from ML and DL methods for various types of applications. These methods…

In this paper, we propose an algorithm that targets contamination and eavesdropping adversaries. We consider the case when the number of independent packets available to the eavesdropper is less than the multicast capacity of the network.…

Honeypots are decoy systems mimicking real system components designed to defend against cyber attacks. Recently, LLMs increasingly serve as simulation backbones for honeypots. They enable defenders to construct high-interaction honeypots…

DNS over TLS (DoT) and DNS over HTTPS (DoH) encrypt DNS to guard user privacy by hiding DNS resolutions from passive adversaries. Yet, past attacks have shown that encrypted DNS is still sensitive to traffic analysis. As a consequence, RFC…

Federated Learning (FL) enables collaborative model training while preserving data privacy by keeping raw data locally stored on client devices, preventing access from other clients or the central server. However, recent studies reveal that…

Gradient inversion attack (or input recovery from gradient) is an emerging threat to the security and privacy preservation of Federated learning, whereby malicious eavesdroppers or participants in the protocol can recover (partially) the…

Split Learning (SL) is a collaborative learning approach that improves privacy by keeping data on the client-side while sharing only the intermediate output with a server. However, the distributed nature of SL introduces new security…

Recent work has highlighted the risks of intellectual property (IP) piracy of deep learning (DL) models from the side-channel leakage of DL hardware accelerators. In response, to provide side-channel leakage resiliency to DL hardware…

Encrypted deduplication combines encryption and deduplication to simultaneously achieve both data security and storage efficiency. State-of-the-art encrypted deduplication systems mainly build on deterministic encryption to preserve…

Data privacy is critical in instilling trust and empowering the societal pacts of modern technology-driven democracies. Unfortunately, it is under continuous attack by overreaching or outright oppressive governments, including some of the…

As the quantum research community expands and new quantum algorithms are created and implemented, it is essential to consider the security implications and potential threats that could lead to the compromise the information processed by…

This paper presents DLHT, a concurrent in-memory hashtable. Despite efforts to optimize hashtables, that go as far as sacrificing core functionality, state-of-the-art designs still incur multiple memory accesses per request and block…

Advanced Persistent Threat (APT) attack usually refers to the form of long-term, covert and sustained attack on specific targets, with an adversary using advanced attack techniques to destroy the key facilities of an organization. APT…

The deep learning (DL) has been penetrating daily life in many domains, how to keep the DL model inference secure and sample privacy in an encrypted environment has become an urgent and increasingly important issue for various…