Related papers: Positional-Unigram Byte Models for Generalized TLS…

Deployed large language models (LLMs) often rely on speculative decoding, a technique that generates and verifies multiple candidate tokens in parallel, to improve throughput and latency. In this work, we reveal a new side-channel whereby…

Large Language Models (LLMs) have shown impressive performance in mathematical reasoning tasks when guided by Chain-of-Thought (CoT) prompting. However, they tend to produce highly confident yet incorrect outputs, which poses significant…

In computer security, designing a robust intrusion detection system is one of the most fundamental and important problems. In this paper, we propose a system-call language-modeling approach for designing anomaly-based host intrusion…

We study blind fingerprinting, where the host sequence into which fingerprints are embedded is partially or completely unknown to the decoder. This problem relates to a multiuser version of the Gel'fand-Pinsker problem. The number of…

Federated Learning (FL) is increasingly adopted as a decentralized machine learning paradigm due to its capability to preserve data privacy by training models without centralizing user data. However, FL is susceptible to indirect privacy…

Common privacy enhancing technologies fail to effectively hide certain statistical aspects of encrypted traffic, namely individual packets length, packets direction and, packets timing. Recent researches have shown that using such…

TLS is the most widely used cryptographic protocol on the Internet. While many recent studies focused on its use in HTTPS, none so far analyzed TLS usage in e-mail related protocols, which often carry highly sensitive information. Since…

TLS 1.3 marks a significant departure from previous versions of the Transport Layer Security protocol (TLS). The new version offers a simplified protocol flow, more secure cryptographic primitives, and new features to improve performance,…

Self-Supervised Learning (SSL) is crucial for real-world applications, especially in data-hungry domains such as healthcare and self-driving cars. In addition to a lack of labeled data, these applications also suffer from distributional…

Federated Learning (FL) has emerged as a promising approach for privacy-preserving machine learning, particularly in sensitive domains such as healthcare. In this context, the TRUSTroke project aims to leverage FL to assist clinicians in…

Ensembling Large Language Models (LLMs) has gained attention as a promising approach to surpass the performance of individual models by leveraging their complementary strengths. In particular, aggregating models' next-token probability…

In the past decade, several small-scale quantum key distribution networks have been established. However, the deployment of large-scale quantum networks depends on the development of quantum repeaters, quantum channels, quantum memories,…

Modern HTTPS mechanisms such as Encrypted Client Hello (ECH) and encrypted DNS improve privacy but remain vulnerable to website fingerprinting (WF) attacks, where adversaries infer visited sites from encrypted traffic patterns. Existing WF…

The cost of head pose labeling is the main challenge of improving the fine-grained Head Pose Estimation (HPE). Although Self-Supervised Learning (SSL) can be a solution to the lack of huge amounts of labeled data, its efficacy for…

In this paper, we introduce Clid, a Transport Layer Security (TLS) client identification tool based on unsupervised learning on domain names in the server name indication (SNI) field. Clid aims to provide some information on a wide range of…

In this paper bounded model checking of asynchronous concurrent systems is introduced as a promising application area for answer set programming. As the model of asynchronous systems a generalisation of communicating automata, 1-safe Petri…

Current security model in Global System for Mobile Communications (GSM) predominantly use symmetric key cryptography. The rapid advancement of Internet technology facilitates online trading, banking, downloading, emailing using…

Long Short-Term Memory (LSTM) neural network models have become the cornerstone for sequential data modeling in numerous applications, ranging from natural language processing to time series forecasting. Despite their success, the problem…

Malicious domains are part of the landscape of the internet but are becoming more prevalent and more dangerous to both companies and individuals. They can be hosted on variety of technologies and serve an array of content, ranging from…

Large language models have drawn significant attention to the challenge of safe alignment, especially regarding jailbreak attacks that circumvent security measures to produce harmful content. To address the limitations of existing methods…