arXiv subjects

Roberto Bifulco

Publications and source records attributed to Roberto Bifulco.

15 recordsLinked to original sources

arXiv2024

AutoPenBench: Benchmarking Generative Agents for Penetration Testing

Generative AI agents, software systems powered by Large Language Models (LLMs), are emerging as a promising approach to automate cybersecurity tasks. Among the others, penetration testing is a challenging field due to the task complexity and the diverse strategies to simulate cyber-attacks. Despite growing interest and initial studies in automating penetration testing with generative agents, there remains a significant gap in the form of a comprehensive and standard framework for their evaluation and development. This paper introduces AutoPenBench, an open benchmark for evaluating generative agents in automated penetration testing. We present a comprehensive framework that includes 33 tasks, each representing a vulnerable system that the agent has to attack. Tasks are of increasing difficulty levels, including in-vitro and real-world scenarios. We assess the agent performance with generic and specific milestones that allow us to compare results in a standardised manner and understand the limits of the agent under test. We show the benefits of AutoPenBench by testing two agent architectures: a fully autonomous and a semi-autonomous supporting human interaction. We compare their performance and limitations. For example, the fully autonomous agent performs unsatisfactorily achieving a 21% Success Rate (SR) across the benchmark, solving 27% of the simple tasks and only one real-world task. In contrast, the assisted agent demonstrates substantial improvements, with 64% of SR. AutoPenBench allows us also to observe how different LLMs like GPT-4o or OpenAI o1 impact the ability of the agents to complete the tasks. We believe that our benchmark fills the gap with a standard and flexible framework to compare penetration testing agents on a common ground. We hope to extend AutoPenBench along with the research community by making it available under https://github.com/lucagioacchini/auto-pen-bench.

cs.CR↗

arXiv2024

What Did I Do Wrong? Quantifying LLMs' Sensitivity and Consistency to Prompt Engineering

Large Language Models (LLMs) changed the way we design and interact with software systems. Their ability to process and extract information from text has drastically improved productivity in a number of routine tasks. Developers that want to include these models in their software stack, however, face a dreadful challenge: debugging LLMs' inconsistent behavior across minor variations of the prompt. We therefore introduce two metrics for classification tasks, namely sensitivity and consistency, which are complementary to task performance. First, sensitivity measures changes of predictions across rephrasings of the prompt, and does not require access to ground truth labels. Instead, consistency measures how predictions vary across rephrasings for elements of the same class. We perform an empirical comparison of these metrics on text classification tasks, using them as guideline for understanding failure modes of the LLM. Our hope is that sensitivity and consistency will be helpful to guide prompt engineering and obtain LLMs that balance robustness with performance.

cs.LG↗

arXiv2024

AgentQuest: A Modular Benchmark Framework to Measure Progress and Improve LLM Agents

The advances made by Large Language Models (LLMs) have led to the pursuit of LLM agents that can solve intricate, multi-step reasoning tasks. As with any research pursuit, benchmarking and evaluation are key corner stones to efficient and reliable progress. However, existing benchmarks are often narrow and simply compute overall task success. To face these issues, we propose AgentQuest -- a framework where (i) both benchmarks and metrics are modular and easily extensible through well documented and easy-to-use APIs; (ii) we offer two new evaluation metrics that can reliably track LLM agent progress while solving a task. We exemplify the utility of the metrics on two use cases wherein we identify common failure points and refine the agent architecture to obtain a significant performance increase. Together with the research community, we hope to extend AgentQuest further and therefore we make it available under https://github.com/nec-research/agentquest.

cs.AI↗

arXiv2023

Time for aCTIon: Automated Analysis of Cyber Threat Intelligence in the Wild

Cyber Threat Intelligence (CTI) plays a crucial role in assessing risks and enhancing security for organizations. However, the process of extracting relevant information from unstructured text sources can be expensive and time-consuming. Our empirical experience shows that existing tools for automated structured CTI extraction have performance limitations. Furthermore, the community lacks a common benchmark to quantitatively assess their performance. We fill these gaps providing a new large open benchmark dataset and aCTIon, a structured CTI information extraction tool. The dataset includes 204 real-world publicly available reports and their corresponding structured CTI information in STIX format. Our team curated the dataset involving three independent groups of CTI analysts working over the course of several months. To the best of our knowledge, this dataset is two orders of magnitude larger than previously released open source datasets. We then design aCTIon, leveraging recently introduced large language models (GPT3.5) in the context of two custom information extraction pipelines. We compare our method with 10 solutions presented in previous work, for which we develop our own implementations when open-source implementations were lacking. Our results show that aCTIon outperforms previous work for structured CTI extraction with an improvement of the F1-score from 10%points to 50%points across all tasks.

cs.CR↗

arXiv2022

syslrn: Learning What to Monitor for Efficient Anomaly Detection

While monitoring system behavior to detect anomalies and failures is important, existing methods based on log-analysis can only be as good as the information contained in the logs, and other approaches that look at the OS-level software state introduce high overheads. We tackle the problem with syslrn, a system that first builds an understanding of a target system offline, and then tailors the online monitoring instrumentation based on the learned identifiers of normal behavior. While our syslrn prototype is still preliminary and lacks many features, we show in a case study for the monitoring of OpenStack failures that it can outperform state-of-the-art log-analysis systems with little overhead.

cs.LG↗

arXiv2021

The Programmable Data Plane: Abstractions, Architectures, Algorithms, and Applications

Programmable data plane technology enables the systematic reconfiguration of the low-level processing steps applied to network packets and is a key driver in realizing the next generation of network services and applications. This survey presents recent trends and issues in the design and implementation of programmable network devices, focusing on prominent architectures, abstractions, algorithms, and applications proposed, debated, and realized over the past years. We elaborate on the trends that led to the emergence of this technology and highlight the most important pointers from the literature, casting different taxonomies for the field and identifying avenues for future research.

cs.NI↗

arXiv2020

hXDP: Efficient Software Packet Processing on FPGA NICs

FPGA accelerators on the NIC enable the offloading of expensive packet processing tasks from the CPU. However, FPGAs have limited resources that may need to be shared among diverse applications, and programming them is difficult. We present a solution to run Linux's eXpress Data Path programs written in eBPF on FPGAs, using only a fraction of the available hardware resources while matching the performance of high-end CPUs. The iterative execution model of eBPF is not a good fit for FPGA accelerators. Nonetheless, we show that many of the instructions of an eBPF program can be compressed, parallelized or completely removed, when targeting a purpose-built FPGA executor, thereby significantly improving performance. We leverage that to design hXDP, which includes (i) an optimizing-compiler that parallelizes and translates eBPF bytecode to an extended eBPF Instruction-set Architecture defined by us; a (ii) soft-CPU to execute such instructions on FPGA; and (iii) an FPGA-based infrastructure to provide XDP's maps and helper functions as defined within the Linux kernel. We implement hXDP on an FPGA NIC and evaluate it running real-world unmodified eBPF programs. Our implementation is clocked at 156.25MHz, uses about 15% of the FPGA resources, and can run dynamically loaded programs. Despite these modest requirements, it achieves the packet processing throughput of a high-end CPU core and provides a 10x lower packet forwarding latency.

cs.AR↗

arXiv2020

Running Neural Networks on the NIC

In this paper we show that the data plane of commodity programmable (Network Interface Cards) NICs can run neural network inference tasks required by packet monitoring applications, with low overhead. This is particularly important as the data transfer costs to the host system and dedicated machine learning accelerators, e.g., GPUs, can be more expensive than the processing task itself. We design and implement our system -- N3IC -- on two different NICs and we show that it can greatly benefit three different network monitoring use cases that require machine learning inference as first-class-primitive. N3IC can perform inference for millions of network flows per second, while forwarding traffic at 40Gb/s. Compared to an equivalent solution implemented on a general purpose CPU, N3IC can provide 100x lower processing latency, with 1.5x increase in throughput.

cs.DC↗

arXiv2018

In-network Neural Networks

We present N2Net, a system that implements binary neural networks using commodity switching chips deployed in network switches and routers. Our system shows that these devices can run simple neural network models, whose input is encoded in the network packets' header, at packet processing speeds (billions of packets per second). Furthermore, our experience highlights that switching chips could support even more complex models, provided that some minor and cheap modifications to the chip's design are applied. We believe N2Net provides an interesting building block for future end-to-end networked systems.

cs.DC↗

arXiv2017

Re-designing Dynamic Content Delivery in the Light of a Virtualized Infrastructure

We explore the opportunities and design options enabled by novel SDN and NFV technologies, by re-designing a dynamic Content Delivery Network (CDN) service. Our system, named MOSTO, provides performance levels comparable to that of a regular CDN, but does not require the deployment of a large distributed infrastructure. In the process of designing the system, we identify relevant functions that could be integrated in the future Internet infrastructure. Such functions greatly simplify the design and effectiveness of services such as MOSTO. We demonstrate our system using a mixture of simulation, emulation, testbed experiments and by realizing a proof-of-concept deployment in a planet-wide commercial cloud system.

cs.NI↗

arXiv2017

Relaxing state-access constraints in stateful programmable data planes

Supporting the programming of stateful packet forwarding functions in hardware has recently attracted the interest of the research community. When designing such switching chips, the challenge is to guarantee the ability to program functions that can read and modify data plane's state, while keeping line rate performance and state consistency. Current state-of-the-art designs are based on a very conservative all-or-nothing model: programmability is limited only to those functions that are guaranteed to sustain line rate, with any traffic workload. In effect, this limits the maximum time to execute state update operations. In this paper, we explore possible options to relax these constraints by using simulations on real traffic traces. We then propose a model in which functions can be executed in a larger but bounded time, while preventing data hazards with memory locking. We present results showing that such flexibility can be supported with little or no throughput degradation.

cs.NI↗

arXiv2017

Relaxing constraints in stateful network data plane design

Supporting programmable states in the data plane of a forwarding element, e.g., a switch or a NIC, has recently attracted the interest of the research community, which is now looking for the right abstraction to enable the programming of stateful network functions in hardware at line rate. We challenge the conservative assumptions of state-of-the-art abstractions in this field, e.g. always assuming minimum size packets arriving back-to-back. Using trace-based simulations we show that by making more realistic assumptions on the traffic characteristics, e.g. larger average packet size, we can relax the design constraints that currently limit the set of functions that can be implemented at line rate, allowing for more complex functions, with no harm for performance.

cs.NI↗

arXiv2016

Towards a Stateful Forwarding Abstraction to Implement Scalable Network Functions in Software and Hardware

An effective packet processing abstraction that leverages software or hardware acceleration techniques can simplify the implementation of high-performance virtual network functions. In this paper, we explore the suitability of SDN switches' stateful forwarding abstractions to model accelerated functions in both software and hardware accelerators, such as optimized software switches and FPGA-based NICs. In particular, we select an Extended Finite State Machine abstraction and demonstrate its suitability by implementing the Linux's iptables interface. By doing so, we provide the acceleration of functions such as stateful firewalls, load balancers and dynamic NATs. We find that supporting a flow-level programming consistency model is an important feature of a programming abstraction in this context. Furthermore, we demonstrate that such a model simplifies the scaling of the system when implemented in software, enabling efficient multi-core processing without harming state consistency.

cs.NI↗

arXiv2016

On-the-Fly TCP Acceleration with Miniproxy

TCP proxies are basic building blocks for many advanced middleboxes. In this paper we present Miniproxy, a TCP proxy built on top of a specialized minimalistic cloud operating system. Miniproxy's connection handling performance is comparable to that of full-fledged GNU/Linux TCP proxy implementations, but its minimalistic footprint enables new use cases. Specifically, Miniproxy requires as little as 6 MB to run and boots in tens of milliseconds, enabling massive consolidation, on-the-fly instantiation and edge cloud computing scenarios. We demonstrate the benefits of Miniproxy by implementing and evaluating a TCP acceleration use case.

cs.NI↗

arXiv2015

Fingerprinting Software-defined Networks

Software-defined networking (SDN) eases network management by centralizing the control plane and separating it from the data plane. The separation of planes in SDN, however, introduces new vulnerabilities in SDN networks since the difference in processing packets at each plane allows an adversary to fingerprint the network's packet-forwarding logic. In this paper, we study the feasibility of fingerprinting the controller-switch interactions by a remote adversary, whose aim is to acquire knowledge about specific flow rules that are installed at the switches. This knowledge empowers the adversary with a better understanding of the network's packet-forwarding logic and exposes the network to a number of threats. In our study, we collect measurements from hosts located across the globe using a realistic SDN network comprising of OpenFlow hardware and software switches. We show that, by leveraging information from the RTT and packet-pair dispersion of the exchanged packets, fingerprinting attacks on SDN networks succeed with overwhelming probability. We also show that these attacks are not restricted to active adversaries, but can be equally mounted by passive adversaries that only monitor traffic exchanged with the SDN network. Finally, we discuss the implications of these attacks on the security of SDN networks, and we present and evaluate an efficient countermeasure to strengthen SDN networks against fingerprinting. Our results demonstrate the effectiveness of our countermeasure in deterring fingerprinting attacks on SDN networks.

cs.CR↗