Related papers: Information Flow Control in Machine Learning throu…
A model of cloud services is emerging whereby a few trusted providers manage the underlying hardware and communications whereas many companies build on this infrastructure to offer higher level, cloud-hosted PaaS services and/or SaaS…
Information-Centric Networks place content as the narrow waist of the network architecture. This allows to route based upon the content name, and not based upon the locations of the content consumer and producer. However, current Internet…
The subjective experience of consciousness is at once familiar and yet deeply mysterious. Strategies exploring the top-down mechanisms of conscious thought within the human brain have been unable to produce a generalized explanatory theory…
Large Language Models (LLMs) are rapidly becoming commodity components of larger software systems. This poses natural security and privacy problems: poisoned data retrieved from one component can change the model's behavior and compromise…
We investigate security concerns of the emergent instruction tuning paradigm, that models are trained on crowdsourced datasets with task instructions to achieve superior performance. Our studies demonstrate that an attacker can inject…
In modern communication networks driven by 5G and the Internet of Things (IoT), effective network traffic flow classification is crucial for Quality of Service (QoS) management and security. Traditional centralized machine learning…
The rise of serverless computing provides an opportunity to rethink cloud security. We present an approach for securing serverless systems using a novel form of dynamic information flow control (IFC). We show that in serverless…
We introduce a new perspective into the field of quantitative information flow (QIF) analysis that invites the community to bound the leakage, reported by QIF quantifiers, by a range consistent with the size of a program's secret input…
Adversarial attacks for machine learning models have become a highly studied topic both in academia and industry. These attacks, along with traditional security threats, can compromise confidentiality, integrity, and availability of…
Learning from data of past tasks can substantially improve the accuracy of mechatronic systems. Often, for fast and safe learning a model of the system is required. The aim of this paper is to develop a model-free approach for fast and safe…
In this paper, we address the problem of reference tracking for uncertain nonlinear systems. Since collecting data from the target system (i.e., the system of interest) is often challenging, our objective is to design optimal controllers…
The rapidly growing demand for high-quality data in Large Language Models (LLMs) has intensified the need for scalable, reliable, and semantically rich data preparation pipelines. However, current practices remain dominated by ad-hoc…
In the realm of control systems, model predictive control (MPC) has exhibited remarkable potential; however, its reliance on accurate models and substantial computational resources has hindered its broader application, especially within…
Poor data quality limits the advantageous power of Machine Learning (ML) and weakens high-performing ML software systems. Nowadays, data are more prone to the risk of poor quality due to their increasing volume and complexity. Therefore,…
Modern nonlinear control theory seeks to endow systems with properties of stability and safety, and have been deployed successfully in multiple domains. Despite this success, model uncertainty remains a significant challenge in synthesizing…
Modern agentic systems allow Large Language Model (LLM) agents to tackle complex tasks through extensive tool usage, forming structured control flows of tool selection and execution. Existing security analyses often treat these control…
In the expanding field of machine learning, federated learning has emerged as a pivotal methodology for distributed data environments, ensuring privacy while leveraging decentralized data sources. However, the heterogeneity of client data…
We present Labeled Input Output in F* (LIO*), a verified framework that enforces information flow control (IFC) policies developed in F* and automatically extracted to C. Inspired by LIO, we encapsulated IFC policies into effects, but using…
Machine Learning (ML) and Artificial Intelligence (AI) have a dependency on data sources to train, improve and make predictions through their algorithms. With the digital revolution and current paradigms like the Internet of Things, this…
SAFE is a clean-slate design for a highly secure computer system, with pervasive mechanisms for tracking and limiting information flows. At the lowest level, the SAFE hardware supports fine-grained programmable tags, with efficient and…