arXiv subjects

Lucas C. Cordeiro

Publications and source records attributed to Lucas C. Cordeiro.

At least 37 records · Page 2Linked to original sources

arXiv2024

Was it Slander? Towards Exact Inversion of Generative Language Models

Training large language models (LLMs) requires a substantial investment of time and money. To get a good return on investment, the developers spend considerable effort ensuring that the model never produces harmful and offensive outputs. However, bad-faith actors may still try to slander the reputation of an LLM by publicly reporting a forged output. In this paper, we show that defending against such slander attacks requires reconstructing the input of the forged output or proving that it does not exist. To do so, we propose and evaluate a search based approach for targeted adversarial attacks for LLMs. Our experiments show that we are rarely able to reconstruct the exact input of an arbitrary output, thus demonstrating that LLMs are still vulnerable to slander attacks.

cs.CR↗

arXiv2024

Synthetic Data Aided Federated Learning Using Foundation Models

In heterogeneous scenarios where the data distribution amongst the Federated Learning (FL) participants is Non-Independent and Identically distributed (Non-IID), FL suffers from the well known problem of data heterogeneity. This leads the performance of FL to be significantly degraded, as the global model tends to struggle to converge. To solve this problem, we propose Differentially Private Synthetic Data Aided Federated Learning Using Foundation Models (DPSDA-FL), a novel data augmentation strategy that aids in homogenizing the local data present on the clients' side. DPSDA-FL improves the training of the local models by leveraging differentially private synthetic data generated from foundation models. We demonstrate the effectiveness of our approach by evaluating it on the benchmark image dataset: CIFAR-10. Our experimental results have shown that DPSDA-FL can improve class recall and classification accuracy of the global model by up to 26% and 9%, respectively, in FL with Non-IID issues.

cs.LG↗

arXiv2024

ESBMC-Python: A Bounded Model Checker for Python Programs

This paper introduces a tool for verifying Python programs, which, using type annotation and front-end processing, can harness the capabilities of a bounded model-checking (BMC) pipeline. It transforms an input program into an abstract syntax tree to infer and add type information. Then, it translates Python expressions and statements into an intermediate representation. Finally, it converts this description into formulae evaluated with satisfiability modulo theories (SMT) solvers. The proposed approach was realized with the efficient SMT-based bounded model checker (ESBMC), which resulted in a tool called ESBMC-Python, the first BMC-based Python-code verifier. Experimental results, with a test suite specifically developed for this purpose, showed its effectiveness, where successful and failed tests were correctly evaluated. Moreover, it found a real problem in the Ethereum Consensus Specification.

cs.SE↗

arXiv2024

A New Era in Software Security: Towards Self-Healing Software via Large Language Models and Formal Verification

This paper introduces an innovative approach that combines Large Language Models (LLMs) with Formal Verification strategies for automatic software vulnerability repair. Initially, we employ Bounded Model Checking (BMC) to identify vulnerabilities and extract counterexamples. These counterexamples are supported by mathematical proofs and the stack trace of the vulnerabilities. Using a specially designed prompt, we combine the original source code with the identified vulnerability, including its stack trace and counterexample that specifies the line number and error type. This combined information is then fed into an LLM, which is instructed to attempt to fix the code. The new code is subsequently verified again using BMC to ensure the fix succeeded. We present the ESBMC-AI framework as a proof of concept, leveraging the well-recognized and industry-adopted Efficient SMT-based Context-Bounded Model Checker (ESBMC) and a pre-trained transformer model to detect and fix errors in C programs, particularly in critical software components. We evaluated our approach on 50,000 C programs randomly selected from the FormAI dataset with their respective vulnerability classifications. Our results demonstrate ESBMC-AI's capability to automate the detection and repair of issues such as buffer overflow, arithmetic overflow, and pointer dereference failures with high accuracy. ESBMC-AI is a pioneering initiative, integrating LLMs with BMC techniques, offering potential integration into the continuous integration and deployment (CI/CD) process within the software development lifecycle.

cs.SE↗

arXiv2024

Interval Analysis in Industrial-Scale BMC Software Verifiers: A Case Study

Bounded Model Checking (BMC) is a widely used software verification technique. Despite its successes, the technique has several limiting factors, from state-space explosion to lack of completeness. Over the years, interval analysis has repeatedly been proposed as a partial solution to these limitations. In this work, we evaluate whether the computational cost of interval analysis yields significant enough improvements in BMC's performance to justify its use. In more detail, we quantify the benefits of interval analysis on two benchmarks: the Intel Core Power Management firmware and 9537 programs in the ReachSafety category of the International Competition on Software Verification. Our results show that interval analysis is essential in solving 203 unique benchmarks.

cs.SE↗

arXiv2024

Verifying components of Arm(R) Confidential Computing Architecture with ESBMC

Realm Management Monitor (RMM) is an essential firmware component within the recent Arm Confidential Computing Architecture (Arm CCA). Previous work applies formal techniques to verify the specification and prototype reference implementation of RMM. However, relying solely on a single verification tool may lead to the oversight of certain bugs or vulnerabilities. This paper discusses the application of ESBMC, a state-of-the-art Satisfiability Modulo Theories (SMT)-based software model checker, to further enhance RRM verification. We demonstrate ESBMC's ability to precisely parse the source code and identify specification failures within a reasonable time frame. Moreover, we propose potential improvements for ESBMC to enhance its efficiency for industry engineers. This work contributes to exploring the capabilities of formal verification techniques in real-world scenarios and suggests avenues for further improvements to better meet industrial verification needs.

cs.SE↗

arXiv2024

Automated Repair of AI Code with Large Language Models and Formal Verification

The next generation of AI systems requires strong safety guarantees. This report looks at the software implementation of neural networks and related memory safety properties, including NULL pointer deference, out-of-bound access, double-free, and memory leaks. Our goal is to detect these vulnerabilities, and automatically repair them with the help of large language models. To this end, we first expand the size of NeuroCodeBench, an existing dataset of neural network code, to about 81k programs via an automated process of program mutation. Then, we verify the memory safety of the mutated neural network implementations with ESBMC, a state-of-the-art software verifier. Whenever ESBMC spots a vulnerability, we invoke a large language model to repair the source code. For the latest task, we compare the performance of various state-of-the-art prompt engineering techniques, and an iterative approach that repeatedly calls the large language model.

cs.SE↗

arXiv2024

FuSeBMC v4: Improving code coverage with smart seeds via BMC, fuzzing and static analysis

Bounded model checking (BMC) and fuzzing techniques are among the most effective methods for detecting errors and security vulnerabilities in software. However, there are still shortcomings in detecting these errors due to the inability of existent methods to cover large areas in target code. We propose FuSeBMC v4, a test generator that synthesizes seeds with useful properties, that we refer to as smart seeds, to improve the performance of its hybrid fuzzer thereby achieving high C program coverage. FuSeBMC works by first analyzing and incrementally injecting goal labels into the given C program to guide BMC and Evolutionary Fuzzing engines. After that, the engines are employed for an initial period to produce the so-called smart seeds. Finally, the engines are run again, with these smart seeds as starting seeds, in an attempt to achieve maximum code coverage / find bugs. During both seed generation and normal running, coordination between the engines is aided by the Tracer subsystem. This subsystem carries out additional coverage analysis and updates a shared memory with information on goals covered so far. Furthermore, the Tracer evaluates test cases dynamically to convert cases into seeds for subsequent test fuzzing. Thus, the BMC engine can provide the seed that allows the fuzzing engine to bypass complex mathematical guards (e.g., input validation). As a result, we received three awards for participation in the fourth international competition in software testing (Test-Comp 2022), outperforming all state-of-the-art tools in every category, including the coverage category.

cs.SE↗

arXiv2024

FuSeBMC AI: Acceleration of Hybrid Approach through Machine Learning

We present FuSeBMC-AI, a test generation tool grounded in machine learning techniques. FuSeBMC-AI extracts various features from the program and employs support vector machine and neural network models to predict a hybrid approach optimal configuration. FuSeBMC-AI utilizes Bounded Model Checking and Fuzzing as back-end verification engines. FuSeBMC-AI outperforms the default configuration of the underlying verification engine in certain cases while concurrently diminishing resource consumption.

cs.CR↗

arXiv2024

The FormAI Dataset: Generative AI in Software Security Through the Lens of Formal Verification

This paper presents the FormAI dataset, a large collection of 112, 000 AI-generated compilable and independent C programs with vulnerability classification. We introduce a dynamic zero-shot prompting technique constructed to spawn diverse programs utilizing Large Language Models (LLMs). The dataset is generated by GPT-3.5-turbo and comprises programs with varying levels of complexity. Some programs handle complicated tasks like network management, table games, or encryption, while others deal with simpler tasks like string manipulation. Every program is labeled with the vulnerabilities found within the source code, indicating the type, line number, and vulnerable function name. This is accomplished by employing a formal verification method using the Efficient SMT-based Bounded Model Checker (ESBMC), which uses model checking, abstract interpretation, constraint programming, and satisfiability modulo theories to reason over safety/security properties in programs. This approach definitively detects vulnerabilities and offers a formal model known as a counterexample, thus eliminating the possibility of generating false positive reports. We have associated the identified vulnerabilities with Common Weakness Enumeration (CWE) numbers. We make the source code available for the 112, 000 programs, accompanied by a separate file containing the vulnerabilities detected in each program, making the dataset ideal for training LLMs and machine learning algorithms. Our study unveiled that according to ESBMC, 51.24% of the programs generated by GPT-3.5 contained vulnerabilities, thereby presenting considerable risks to software safety and security.

cs.DB↗

arXiv2024

Revolutionizing Cyber Threat Detection with Large Language Models: A privacy-preserving BERT-based Lightweight Model for IoT/IIoT Devices

The field of Natural Language Processing (NLP) is currently undergoing a revolutionary transformation driven by the power of pre-trained Large Language Models (LLMs) based on groundbreaking Transformer architectures. As the frequency and diversity of cybersecurity attacks continue to rise, the importance of incident detection has significantly increased. IoT devices are expanding rapidly, resulting in a growing need for efficient techniques to autonomously identify network-based attacks in IoT networks with both high precision and minimal computational requirements. This paper presents SecurityBERT, a novel architecture that leverages the Bidirectional Encoder Representations from Transformers (BERT) model for cyber threat detection in IoT networks. During the training of SecurityBERT, we incorporated a novel privacy-preserving encoding technique called Privacy-Preserving Fixed-Length Encoding (PPFLE). We effectively represented network traffic data in a structured format by combining PPFLE with the Byte-level Byte-Pair Encoder (BBPE) Tokenizer. Our research demonstrates that SecurityBERT outperforms traditional Machine Learning (ML) and Deep Learning (DL) methods, such as Convolutional Neural Networks (CNNs) or Recurrent Neural Networks (RNNs), in cyber threat detection. Employing the Edge-IIoTset cybersecurity dataset, our experimental analysis shows that SecurityBERT achieved an impressive 98.2% overall accuracy in identifying fourteen distinct attack types, surpassing previous records set by hybrid solutions such as GAN-Transformer-based architectures and CNN-LSTM models. With an inference time of less than 0.15 seconds on an average CPU and a compact model size of just 16.7MB, SecurityBERT is ideally suited for real-life traffic analysis and a suitable choice for deployment on resource-constrained IoT devices.

cs.CR↗

arXiv2023

ESBMC v7.4: Harnessing the Power of Intervals

ESBMC implements many state-of-the-art techniques for model checking. We report on new and improved features that allow us to obtain verification results for previously unsupported programs and properties. ESBMC employs a new static interval analysis of expressions in programs to increase verification performance. This includes interval-based reasoning over booleans and integers, forward and backward contractors, and particular optimizations related to singleton intervals because of their ubiquity. Other relevant improvements concern the verification of concurrent programs, as well as several operational models, internal ones, and also those of libraries such as pthread and the C mathematics library. An extended memory safety analysis now allows tracking of memory leaks that are considered still reachable.

cs.SE↗

arXiv2023

Finding Software Vulnerabilities in Open-Source C Projects via Bounded Model Checking

Computer-based systems have solved several domain problems, including industrial, military, education, and wearable. Nevertheless, such arrangements need high-quality software to guarantee security and safety as both are mandatory for modern software products. We advocate that bounded model-checking techniques can efficiently detect vulnerabilities in general software systems. However, such an approach struggles to scale up and verify extensive code bases. Consequently, we have developed and evaluated a methodology to verify large software systems using a state-of-the-art bounded model checker. In particular, we pre-process input source-code files and guide the respective model checker to explore them systematically. Moreover, the proposed scheme includes a function-wise prioritization strategy, which readily provides results for code entities according to a scale of importance. Experimental results using a real implementation of the proposed methodology show that it can efficiently verify large software systems. Besides, it presented low peak memory allocation when executed. We have evaluated our approach by verifying twelve popular open-source C projects, where we have found real software vulnerabilities that their developers confirmed.

cs.CR↗

arXiv2023

A Privacy-Preserving and Accountable Billing Protocol for Peer-to-Peer Energy Trading Markets

This paper proposes a privacy-preserving and accountable billing (PA-Bill) protocol for trading in peer-to-peer energy markets, addressing situations where there may be discrepancies between the volume of energy committed and delivered. Such discrepancies can lead to challenges in providing both privacy and accountability while maintaining accurate billing. To overcome these challenges, a universal cost splitting mechanism is proposed that prioritises privacy and accountability. It leverages a homomorphic encryption cryptosystem to provide privacy and employs blockchain technology to establish accountability. A dispute resolution mechanism is also introduced to minimise the occurrence of erroneous bill calculations while ensuring accountability and non-repudiation throughout the billing process. Our evaluation demonstrates that PA-Bill offers an effective billing mechanism that maintains privacy and accountability in peer-to-peer energy markets utilising a semi-decentralised approach.

cs.CR↗

arXiv2023

QNNRepair: Quantized Neural Network Repair

We present QNNRepair, the first method in the literature for repairing quantized neural networks (QNNs). QNNRepair aims to improve the accuracy of a neural network model after quantization. It accepts the full-precision and weight-quantized neural networks and a repair dataset of passing and failing tests. At first, QNNRepair applies a software fault localization method to identify the neurons that cause performance degradation during neural network quantization. Then, it formulates the repair problem into a linear programming problem of solving neuron weights parameters, which corrects the QNN's performance on failing tests while not compromising its performance on passing tests. We evaluate QNNRepair with widely used neural network architectures such as MobileNetV2, ResNet, and VGGNet on popular datasets, including high-resolution images. We also compare QNNRepair with the state-of-the-art data-free quantization method SQuant. According to the experiment results, we conclude that QNNRepair is effective in improving the quantized model's performance in most cases. Its repaired models have 24% higher accuracy than SQuant's in the independent validation set, especially for the ImageNet dataset.

cs.LG↗

arXiv2023

NeuroCodeBench: a plain C neural network benchmark for software verification

Safety-critical systems with neural network components require strong guarantees. While existing neural network verification techniques have shown great progress towards this goal, they cannot prove the absence of software faults in the network implementation. This paper presents NeuroCodeBench - a verification benchmark for neural network code written in plain C. It contains 32 neural networks with 607 safety properties divided into 6 categories: maths library, activation functions, error-correcting networks, transfer function approximation, probability density estimation and reinforcement learning. Our preliminary evaluation shows that state-of-the-art software verifiers struggle to provide correct verdicts, due to their incomplete support of the standard C mathematical library and the complexity of larger neural networks.

cs.SE↗

arXiv2023

ESBMC v7.3: Model Checking C++ Programs using Clang AST

This paper introduces ESBMC v7.3, the latest Efficient SMT-Based Context-Bounded Model Checker version, which now incorporates a new clang-based C++ front-end. While the previous CPROVER-based front-end served well for handling C++03 programs, it encountered challenges keeping up with the evolving C++ language. As new language and library features were added in each C++ version, the limitations of the old front-end became apparent, leading to difficult-to-maintain code. Consequently, modern C++ programs were challenging to verify. To overcome this obstacle, we redeveloped the front-end, opting for a more robust approach using clang. The new front-end efficiently traverses the Abstract Syntax Tree (AST) in-memory using clang APIs and transforms each AST node into ESBMC's Intermediate Representation. Through extensive experimentation, our results demonstrate that ESBMC v7.3 with the new front-end significantly reduces parse and conversion errors, enabling successful verification of a wide range of C++ programs, thereby outperforming previous ESBMC versions.

cs.LO↗

arXiv2023

Poisoning Attacks in Federated Edge Learning for Digital Twin 6G-enabled IoTs: An Anticipatory Study

Federated edge learning can be essential in supporting privacy-preserving, artificial intelligence (AI)-enabled activities in digital twin 6G-enabled Internet of Things (IoT) environments. However, we need to also consider the potential of attacks targeting the underlying AI systems (e.g., adversaries seek to corrupt data on the IoT devices during local updates or corrupt the model updates); hence, in this article, we propose an anticipatory study for poisoning attacks in federated edge learning for digital twin 6G-enabled IoT environments. Specifically, we study the influence of adversaries on the training and development of federated learning models in digital twin 6G-enabled IoT environments. We demonstrate that attackers can carry out poisoning attacks in two different learning settings, namely: centralized learning and federated learning, and successful attacks can severely reduce the model's accuracy. We comprehensively evaluate the attacks on a new cyber security dataset designed for IoT applications with three deep neural networks under the non-independent and identically distributed (Non-IID) data and the independent and identically distributed (IID) data. The poisoning attacks, on an attack classification problem, can lead to a decrease in accuracy from 94.93% to 85.98% with IID data and from 94.18% to 30.04% with Non-IID.

cs.CR↗