arXiv subjects

Nuno Neves

Publications and source records attributed to Nuno Neves.

7 recordsLinked to original sources

arXiv2026

EPAC: The Last Dance

This paper presents EPAC, a RISC-V-based accelerator chip developed within the European Processor Initiative (EPI) as part of a multi-year, multi-partner effort to build a European HPC processor ecosystem. EPAC is implemented in GlobalFoundries 22FDX (GF22FDX) technology, covers an area of 27 sq mm with approximately 0.3 billion transistors, and integrates three distinct RISC-V compute tiles targeting different workload classes: VEC, a vector processing tile for double-precision HPC workloads; STX, a many-core tile optimized for stencil and machine learning computations; and VRP, a variable-precision tile for iterative numerical solvers requiring extended floating-point formats. All tiles are connected through a Coherent Hub Interface (CHI) based network-on-chip with a distributed L2 cache system and communicate with external memory via a SerDes link. The chip was taped out in GF22FDX technology and successfully brought up, with all major IP blocks validated. This paper describes the architecture of each tile and the uncore infrastructure, the integration and physical implementation process, and the board-level bring-up activities. It also reflects on the engineering and coordination lessons learned from a full chip design effort distributed across academic and industrial partners in Europe.

cs.AR↗

arXiv2025

Mingling with the Good to Backdoor Federated Learning

Federated learning (FL) is a decentralized machine learning technique that allows multiple entities to jointly train a model while preserving dataset privacy. However, its distributed nature has raised various security concerns, which have been addressed by increasingly sophisticated defenses. These protections utilize a range of data sources and metrics to, for example, filter out malicious model updates, ensuring that the impact of attacks is minimized or eliminated. This paper explores the feasibility of designing a generic attack method capable of installing backdoors in FL while evading a diverse array of defenses. Specifically, we focus on an attacker strategy called MIGO, which aims to produce model updates that subtly blend with legitimate ones. The resulting effect is a gradual integration of a backdoor into the global model, often ensuring its persistence long after the attack concludes, while generating enough ambiguity to hinder the effectiveness of defenses. MIGO was employed to implant three types of backdoors across five datasets and different model architectures. The results demonstrate the significant threat posed by these backdoors, as MIGO consistently achieved exceptionally high backdoor accuracy (exceeding 90%) while maintaining the utility of the main task. Moreover, MIGO exhibited strong evasion capabilities against ten defenses, including several state-of-the-art methods. When compared to four other attack strategies, MIGO consistently outperformed them across most configurations. Notably, even in extreme scenarios where the attacker controls just 0.1% of the clients, the results indicate that successful backdoor insertion is possible if the attacker can persist for a sufficient number of rounds.

cs.CR↗

arXiv2019

Statically Detecting Vulnerabilities by Processing Programming Languages as Natural Languages

Web applications continue to be a favorite target for hackers due to a combination of wide adoption and rapid deployment cycles, which often lead to the introduction of high impact vulnerabilities. Static analysis tools are important to search for bugs automatically in the program source code, supporting developers on their removal. However, building these tools requires programming the knowledge on how to discover the vulnerabilities. This paper presents an alternative approach in which tools learn to detect flaws automatically by resorting to artificial intelligence concepts, more concretely to natural language processing. The approach employs a sequence model to learn to characterize vulnerabilities based on an annotated corpus. Afterwards, the model is utilized to discover and identify vulnerabilities in the source code. It was implemented in the DEKANT tool and evaluated experimentally with a large set of PHP applications and WordPress plugins. Overall, we found several hundred vulnerabilities belonging to 12 classes of input validation vulnerabilities, where 62 of them were zero-day.

cs.CR↗

arXiv2018

SITAN: Services for Fault-Tolerant Ad Hoc Networks with Unknown Participants

The evolution of mobile devices with various capabilities (e.g., smartphones and tablets), together with their ability to collaborate in impromptu ad hoc networks, opens new opportunities for the design of innovative distributed applications. The development of these applications needs to address several difficulties, such as the unreliability of the network, the imprecise set of participants, or the presence of malicious nodes. In this paper we describe a middleware, called SITAN, that offers a number of communication, group membership and coordination services specially conceived for these settings. These services are implemented by a stack of Byzantine fault-tolerant protocols, enabling applications that are built on top of them to operate correctly despite the uncertainty of the environment. The protocol stack was implemented in Android and NS-3, which allowed the experimentation in representative scenarios. Overall, the results show that the protocols are able to finish their execution within a small time window, which is acceptable for various kinds of applications.

cs.DC↗

arXiv2017

Secure Multi-Cloud Virtual Network Embedding

Modern network virtualization platforms enable users to specify custom topologies and arbitrary addressing schemes for their virtual networks. These platforms have, however, been targeting the data center of a single provider, which is insufficient to support (critical) applications that need to be deployed across multiple trust domains, while enforcing diverse security requirements. This paper addresses this limitation by presenting a novel solution for the central resource allocation problem of network virtualization -- the virtual network embedding, which aims to find efficient mappings of virtual network requests onto the substrate network. We improve over the state-of-the-art by considering security as a first-class citizen of virtual networks, while enhancing the substrate infrastructure with resources from multiple cloud providers. Our solution enables the definition of flexible policies in three core elements: on the virtual links, where alternative security compromises can be explored (e.g., encryption); on the virtual switches, supporting various degrees of protection and redundancy if necessary; and on the substrate infrastructure, extending it across multiple clouds, including public and private facilities, with their inherently diverse trust levels associated. We propose an optimal solution to this problem formulated as a Mixed Integer Linear Program (MILP). The results of our evaluation give insight into the trade-offs associated with the inclusion of security demands into network virtualization. In particular, they provide evidence that enhancing the user's virtual networks with security does not preclude high acceptance rates and an efficient use of resources, and allows providers to increase their revenues.

cs.NI↗

arXiv2016

Secure and Dependable Virtual Network Embedding

One of the fundamental problems in network virtualization is Virtual Network Embedding (VNE). The VNE problem deals with finding an effective mapping of the virtual nodes & links onto the substrate network. The recent advances in network virtualization gave cloud operators the ability to extend their cloud computing offerings with virtual networks. This trend, jointly with the increasing evidence of incidents in cloud facilities demonstrate that security and dependability is becoming a critical factor that should be considered by VNE algorithms. In this abstract we propose a VNE solution that considers security and dependability as first class citizens. The resiliency properties of our solution are enhanced by assuming a multiple cloud provider model.

cs.NI↗

arXiv2015

(Literally) above the clouds: virtualizing the network over multiple clouds

Recent SDN-based solutions give cloud providers the opportunity to extend their "as-a-service" model with the offer of complete network virtualization. They provide tenants with the freedom to specify the network topologies and addressing schemes of their choosing, while guaranteeing the required level of isolation among them. These platforms, however, have been targeting the datacenter of a single cloud provider with full control over the infrastructure. This paper extends this concept further by supporting the creation of virtual networks that span across several datacenters, which may belong to distinct cloud providers, while including private facilities owned by the tenant. In order to achieve this, we introduce a new network layer above the existing cloud hypervisors, affording the necessary level of control over the communications while hiding the heterogeneity of the clouds. The benefits of this approach are various, such as enabling finer decisions on where to place the virtual machines (e.g., to fulfill legal requirements), avoiding single points of failure, and potentially decreasing costs. Although our focus in the paper is on architecture design, we also present experimental results of a first prototype of the proposed solution.

cs.NI↗