Related papers: Cats vs. Spectre: An Axiomatic Approach to Modelin…

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…

Adversarial attacks expose important blind spots of deep learning systems. While word- and sentence-level attack scenarios mostly deal with finding semantic paraphrases of the input that fool NLP models, character-level attacks typically…

This works considers challenges of building and usage a formal knowledge base (model), which unites the ATT&CK, CAPEC, CWE, CVE security enumerations. The proposed model can be used to learn relations between attack techniques, attack…

We consider the formulation of a symbolic execution (SE) procedure for functional programs that interact with effectful, opaque libraries. Our procedure allows specifications of libraries and abstract data type (ADT) methods that are…

Latent Chain-of-Thought (Latent CoT) models promise efficient reasoning via continuous representations, yet exhibit puzzling performance inconsistencies: excelling at exploration (ProsQA: 97.0%) but failing at computation (GSM8K: 34.1%). We…

Speculative execution is crucial in enhancing modern processor performance but can introduce Spectre-type vulnerabilities that may leak sensitive information. Detecting Spectre gadgets from programs has been a research focus to enhance the…

Concept explanation is a popular approach for examining how human-interpretable concepts impact the predictions of a model. However, most existing methods for concept explanations are tailored to specific models. To address this issue, this…

The advent of social media has given rise to numerous ethical challenges, with hate speech among the most significant concerns. Researchers are attempting to tackle this problem by leveraging hate-speech detection and employing language…

Early exiting has recently emerged as a promising technique for accelerating large language models (LLMs) by effectively reducing the hardware computation and memory access. In this paper, we present SpecEE, a fast LLM inference engine with…

Adversarial examples --- perturbations to the input of a model that elicit large changes in the output --- have been shown to be an effective way of assessing the robustness of sequence-to-sequence (seq2seq) models. However, these…

State-of-the-art defenses against adversarial patch attacks can now achieve strong certifiable robustness with a marginal drop in model utility. However, this impressive performance typically comes at the cost of 10-100x more inference-time…

Deep learning (DL) has recently emerged as an efficient approach for array processing tasks such as signal detection and direction of arrival. However, DL models lack statistical guarantees and, moreover, are highly susceptible to…

Tree-search-based reasoning methods have significantly enhanced the reasoning capability of large language models (LLMs) by facilitating the exploration of multiple intermediate reasoning steps, i.e., thoughts. However, these methods suffer…

Constant-time (CT) verification tools are commonly used for detecting potential side-channel vulnerabilities in cryptographic libraries. Recently, a new class of tools, called speculative constant-time (SCT) tools, has also been used for…

Model-based safety analysis approaches aim at finding critical failure combinations by analysis of models of the whole system (i.e. software, hardware, failure modes and environment). The advantage of these methods compared to traditional…

Spectre, Meltdown, and related attacks have demonstrated that kernels, hypervisors, trusted execution environments, and browsers are prone to information disclosure through micro-architectural weaknesses. However, it remains unclear as to…

Whenever modern CPUs encounter a conditional branch for which the condition cannot be evaluated yet, they predict the likely branch target and speculatively execute code. Such pipelining is key to optimizing runtime performance and is…

To analyse and verify the safety and security properties of interactive systems, a formal specification might be necessary. There are many types of formal languages and frameworks. The decision regarding what type of formal specification…

Adversaries (hackers) attempting to infiltrate networks frequently face uncertainty in their operational environments. This research explores the ability to model and detect when they exhibit ambiguity aversion, a cognitive bias reflecting…

Attack trees are a popular way to represent and evaluate potential security threats on systems or infrastructures. The goal of this work is to provide a framework allowing to express and check whether an attack tree is consistent with the…