Related papers: Towards Language-Based Mitigation of Traffic Analy…

Nowadays, almost all electronic devices include a communication interface that allows to interact with them, exchange data, or operate their services remotely. The trend toward increased interconnectivity simultaneously increases the…

In this paper, we systematically evaluate the robustness of multi-exit language models against adversarial slowdown. To audit their robustness, we design a slowdown attack that generates natural adversarial text bypassing early-exit points.…

Autoencoder can give rise to an appropriate latent representation of the input data, however, the representation which is solely based on the intrinsic property of the input data, is usually inferior to express some semantic information. A…

Large Language Models face an emerging and critical threat known as latency attacks. Because LLM inference is inherently expensive, even modest slowdowns can translate into substantial operating costs and severe availability risks.…

As large language models (LLMs) become increasingly integrated into real-world applications such as code generation and chatbot assistance, extensive efforts have been made to align LLM behavior with human values, including safety.…

As advances in Deep Neural Networks (DNNs) demonstrate unprecedented levels of performance in many critical applications, their vulnerability to attacks is still an open question. We consider evasion attacks at testing time against Deep…

As Large Language Models (LLMs) become ubiquitous, the challenge of securing them against adversarial "jailbreaking" attacks has intensified. Current defense strategies often rely on computationally expensive external classifiers or brittle…

Network traffic analytics technology is a cornerstone for cyber security systems. We demonstrate its use through three popular and contemporary cyber security applications in intrusion detection, malware analysis and botnet detection.…

With the rapid technological advancements, organizations need to rapidly scale up their information technology (IT) infrastructure viz. hardware, software, and services, at a low cost. However, the dynamic growth in the network services and…

This paper considers an information theoretic model of secure integrated sensing and communication, represented as a wiretap channel with action dependent states. This model allows securing part of a transmitted message against a sensed…

Large language models (LLMs) have made remarkable strides in complex reasoning tasks, but their safety and robustness in reasoning processes remain underexplored. Existing attacks on LLM reasoning are constrained by specific settings or…

We consider the problem of detecting deliberate traffic discrimination on the Internet. Given the complex nature of the Internet, detection of deliberate discrimination is not easy to detect, and tools developed so far suffer from various…

Detecting cyberattacks using Graph Neural Networks (GNNs) has seen promising results recently. Most of the state-of-the-art models that leverage these techniques require labeled examples, hard to obtain in many real-world scenarios. To…

Due to the recent increase in the number of connected devices, the need to promptly detect security issues is emerging. Moreover, the high number of communication flows creates the necessity of processing huge amounts of data. Furthermore,…

Semantic communication has been identified as a core technology for the sixth generation (6G) of wireless networks. Recently, task-oriented semantic communications have been proposed for low-latency inference with limited bandwidth.…

Recent studies show that auto-encoder based approaches successfully perform language generation, smooth sentence interpolation, and style transfer over unseen attributes using unlabelled datasets in a zero-shot manner. The latent space…

The recent discovery of the Spectre and Meltdown attacks represents a watershed moment not just for the field of Computer Security, but also of Programming Languages. This paper explores speculative side-channel attacks and their…

Virtually every connection to an Internet service is preceded by a DNS lookup which is performed without any traffic-level protection, thus enabling manipulation, redirection, surveillance, and censorship. To address these issues, large…

The fragmented nature and asymmetry of local and remote file access and network access, combined with the current lack of robust authenticity and privacy, hamstrings the current internet. The collection of disjoint and often ad-hoc…

Webshell attacks are becoming more common, requiring robust detection mechanisms to protect web applications. The dissertation clearly states two research directions: scanning web application source code and analyzing HTTP traffic to detect…