arXiv subjects

Una-May O'Reilly

Publications and source records attributed to Una-May O'Reilly.

At least 19 recordsLinked to original sources

arXiv2025

Hybrid Privilege Escalation and Remote Code Execution Exploit Chains

Research on exploit chains predominantly focuses on sequences with one type of exploit, e.g., either escalating privileges on a machine or executing remote code. In networks, hybrid exploit chains are critical because of their linkable vulnerabilities. Moreover, developing hybrid exploit chains is challenging because it requires understanding the diverse and independent dependencies and outcomes. We present hybrid chains encompassing privilege escalation (PE) and remote code execution (RCE) exploits. These chains are executable and can span large networks, where numerous potential exploit combinations arise from the large array of network assets, their hardware, software, configurations, and vulnerabilities. The chains are generated by ALFA-Chains, an AI-supported framework for the automated discovery of multi-step PE and RCE exploit chains in networks across arbitrary environments and segmented networks. Through an LLM-based classification, ALFA-Chains describes exploits in Planning Domain Description Language (PDDL). PDDL exploit and network descriptions then use off-the-shelf AI planners to find multiple exploit chains. ALFA-Chains finds 12 unknown chains on an example with a known three-step chain. A red-team exercise validates the executability with Metasploit. ALFA-Chains is efficient, finding an exploit chain in 0.01 seconds in an enterprise network with 83 vulnerabilities, 20 hosts, and 6 subnets. In addition, it is scalable, it finds an exploit chain in an industrial network with 114 vulnerabilities, 200 hosts, and 6 subnets in 3.16 seconds. It is comprehensive, finding 13 exploit chains in 26.26 seconds in the network. Finally, ALFA-Chains demonstrates flexibility across different exploit sources, ability to generalize across diverse network types, and robustness in discovering chains under constrained privilege assumptions.

cs.CR↗

arXiv2025

Evolutionary and Coevolutionary Multi-Agent Design Choices and Dynamics

We investigate two representation alternatives for the controllers of teams of cyber agents. We combine these controller representations with different evolutionary algorithms, one of which introduces a novel LLM-supported mutation operator. Using a cyber security scenario, we evaluate agent learning when one side is trained to compete against a side that does not evolve and when two sides coevolve with each other. This allows us to quantify the relative merits and tradeoffs of representation and algorithm combinations in terms of team performance. Our versions of grammatical evolution algorithms using grammars that allow a controller to be expressed in code-like logic can achieve the best team performance. The scenario also allows us to compare the performance impact and dynamics of coevolution versus evolution under different combinations. Across the algorithms and representations, we observe that coevolution reduces the performance highs and lows of both sides while it induces fluctuations on both sides. In contrast, when only one-side is optimized, performance peaks are higher and is more sustained than when both sides are optimized with coevolution.

cs.NE↗

arXiv2025

Guiding Evolutionary AutoEncoder Training with Activation-Based Pruning Operators

This study explores a novel approach to neural network pruning using evolutionary computation, focusing on simultaneously pruning the encoder and decoder of an autoencoder. We introduce two new mutation operators that use layer activations to guide weight pruning. Our findings reveal that one of these activation-informed operators outperforms random pruning, resulting in more efficient autoencoders with comparable performance to canonically trained models. Prior work has established that autoencoder training is effective and scalable with a spatial coevolutionary algorithm that cooperatively coevolves a population of encoders with a population of decoders, rather than one autoencoder. We evaluate how the same activity-guided mutation operators transfer to this context. We find that random pruning is better than guided pruning, in the coevolutionary setting. This suggests activation-based guidance proves more effective in low-dimensional pruning environments, where constrained sample spaces can lead to deviations from true uniformity in randomization. Conversely, population-driven strategies enhance robustness by expanding the total pruning dimensionality, achieving statistically uniform randomness that better preserves system dynamics. We experiment with pruning according to different schedules and present best combinations of operator and schedule for the canonical and coevolving populations cases.

cs.NE↗

arXiv2025

LLM-Supported Natural Language to Bash Translation

The Bourne-Again Shell (Bash) command-line interface for Linux systems has complex syntax and requires extensive specialized knowledge. Using the natural language to Bash command (NL2SH) translation capabilities of large language models (LLMs) for command composition circumvents these issues. However, the NL2SH performance of LLMs is difficult to assess due to inaccurate test data and unreliable heuristics for determining the functional equivalence of Bash commands. We present a manually verified test dataset of 600 instruction-command pairs and a training dataset of 40,939 pairs, increasing the size of previous datasets by 441% and 135%, respectively. Further, we present a novel functional equivalence heuristic that combines command execution with LLM evaluation of command outputs. Our heuristic can determine the functional equivalence of two Bash commands with 95% confidence, a 16% increase over previous heuristics. Evaluation of popular LLMs using our test dataset and heuristic demonstrates that parsing, in-context learning, in-weight learning, and constrained decoding can improve NL2SH accuracy by up to 32%. Our findings emphasize the importance of dataset quality, execution-based evaluation and translation method for advancing NL2SH translation. Our code is available at https://github.com/westenfelder/NL2SH

cs.CL↗

arXiv2024

Evolving Code with A Large Language Model

Algorithms that use Large Language Models (LLMs) to evolve code arrived on the Genetic Programming (GP) scene very recently. We present LLM GP, a formalized LLM-based evolutionary algorithm designed to evolve code. Like GP, it uses evolutionary operators, but its designs and implementations of those operators radically differ from GP's because they enlist an LLM, using prompting and the LLM's pre-trained pattern matching and sequence completion capability. We also present a demonstration-level variant of LLM GP and share its code. By addressing algorithms that range from the formal to hands-on, we cover design and LLM-usage considerations as well as the scientific challenges that arise when using an LLM for genetic programming.

cs.NE↗

arXiv2023

LLMs Killed the Script Kiddie: How Agents Supported by Large Language Models Change the Landscape of Network Threat Testing

In this paper, we explore the potential of Large Language Models (LLMs) to reason about threats, generate information about tools, and automate cyber campaigns. We begin with a manual exploration of LLMs in supporting specific threat-related actions and decisions. We proceed by automating the decision process in a cyber campaign. We present prompt engineering approaches for a plan-act-report loop for one action of a threat campaign and and a prompt chaining design that directs the sequential decision process of a multi-action campaign. We assess the extent of LLM's cyber-specific knowledge w.r.t the short campaign we demonstrate and provide insights into prompt design for eliciting actionable responses. We discuss the potential impact of LLMs on the threat landscape and the ethical considerations of using LLMs for accelerating threat actor capabilities. We report a promising, yet concerning, application of generative AI to cyber threats. However, the LLM's capabilities to deal with more complex networks, sophisticated vulnerabilities, and the sensitivity of prompts are open questions. This research should spur deliberations over the inevitable advancements in LLM-supported cyber adversarial landscape.

cs.CR↗

arXiv2023

The Facebook Algorithm's Active Role in Climate Advertisement Delivery

Communication strongly influences attitudes on climate change. Within sponsored communication, high spend and high reach advertising dominates. In the advertising ecosystem we can distinguish actors with adversarial stances: organizations with contrarian or advocacy communication goals, who direct the advertisement delivery algorithm to launch ads in different destinations by specifying targets and campaign objectives. We present an observational (N=275,632) and a controlled (N=650) study which collectively indicate that the advertising delivery algorithm could itself be an actor, asserting statistically significant influence over advertisement destinations, characterized by U.S. state, gender type, or age range. This algorithmic behaviour may not entirely be understood by the advertising platform (and its creators). These findings have implications for climate communications and misinformation research, revealing that targeting intentions are not always fulfilled as requested and that delivery itself could be manipulated.

cs.HC↗

arXiv2023

Program Comprehension Does Not Primarily Rely On the Language Centers of the Human Brain

Our goal is to identify brain regions involved in comprehending computer programs. We use functional magnetic resonance imaging (fMRI) to investigate two candidate systems of brain regions which may support this -- the Multiple Demand (MD) system, known to respond to a range of cognitively demanding tasks, and the Language system (LS), known to primarily respond to language stimuli. We devise experiment conditions to isolate the act of code comprehension, and employ a state-of-the-art method to locate brain systems of interest. We administer these experiments in Python (24 participants) and Scratch Jr. (19 participants) - which provides a visual interface to programming, thus eliminating the effect of text in code comprehension. From this robust experiment setup, we find that the Language system is not consistently involved in code comprehension, while the MD is. Further, we find no other brain regions beyond those in the MD to be responsive to code. We also find that variable names, the control flow used in the program, and the types of operations performed do not affect brain responses. We discuss the implications of our findings on the software engineering and CS education communities.

cs.SE↗

arXiv2023

CLAWSAT: Towards Both Robust and Accurate Code Models

We integrate contrastive learning (CL) with adversarial learning to co-optimize the robustness and accuracy of code models. Different from existing works, we show that code obfuscation, a standard code transformation operation, provides novel means to generate complementary `views' of a code that enable us to achieve both robust and accurate code models. To the best of our knowledge, this is the first systematic study to explore and exploit the robustness and accuracy benefits of (multi-view) code obfuscations in code models. Specifically, we first adopt adversarial codes as robustness-promoting views in CL at the self-supervised pre-training phase. This yields improved robustness and transferability for downstream tasks. Next, at the supervised fine-tuning stage, we show that adversarial training with a proper temporally-staggered schedule of adversarial code generation can further improve robustness and accuracy of the pre-trained code model. Built on the above two modules, we develop CLAWSAT, a novel self-supervised learning (SSL) framework for code by integrating $\underline{\textrm{CL}}$ with $\underline{\textrm{a}}$dversarial vie$\underline{\textrm{w}}$s (CLAW) with $\underline{\textrm{s}}$taggered $\underline{\textrm{a}}$dversarial $\underline{\textrm{t}}$raining (SAT). On evaluating three downstream tasks across Python and Java, we show that CLAWSAT consistently yields the best robustness and accuracy ($\textit{e.g.}$ 11$\%$ in robustness and 6$\%$ in accuracy on the code summarization task in Python). We additionally demonstrate the effectiveness of adversarial learning in CLAW by analyzing the characteristics of the loss landscape and interpretability of the pre-trained models.

cs.LG↗

arXiv2021

Evaluating Efficacy of Indoor Non-Pharmaceutical Interventions against COVID-19 Outbreaks with a Coupled Spatial-SIR Agent-Based Simulation Framework

Contagious respiratory diseases, such as COVID-19, depend on sufficiently prolonged exposures for the successful transmission of the underlying pathogen. It is important for organizations to evaluate the efficacy of interventions aiming at mitigating viral transmission among their personnel. We have developed a operational risk assessment simulation framework that couples a spatial agent-based model of movement with a SIR epidemiological model to assess the relative risks of different intervention strategies. By applying our model on MIT's STATA building, we assess the impacts of three possible dimensions of intervention: one-way vs unrestricted movement, population size allowed onsite, and frequency of leaving designated work location for breaks. We find that there is no significant impact made by one-way movement restrictions over unrestricted movement. Instead, we find that a combination of lowering the number of individuals admitted below the current recommendations and advising individuals to reduce the frequency at which they leave their workstations lowers the likelihood of highly connected individuals within the contact networks that emerge, which in turn lowers the overall risk of infection. We discover three classes of possible interventions based on their epidemiological effects. By assuming a direct relationship between data on secondary attack rates and transmissibility in the SIR model, we compare relative infection risk of four respiratory diseases, MERS, SARS, COVID-19, and Measles, within the simulated area, and recommend appropriate intervention guidelines.

q-bio.PE↗

arXiv2021

STRATA: Simple, Gradient-Free Attacks for Models of Code

Neural networks are well-known to be vulnerable to imperceptible perturbations in the input, called adversarial examples, that result in misclassification. Generating adversarial examples for source code poses an additional challenge compared to the domains of images and natural language, because source code perturbations must retain the functional meaning of the code. We identify a striking relationship between token frequency statistics and learned token embeddings: the L2 norm of learned token embeddings increases with the frequency of the token except for the highest-frequnecy tokens. We leverage this relationship to construct a simple and efficient gradient-free method for generating state-of-the-art adversarial examples on models of code. Our method empirically outperforms competing gradient-based methods with less information and less computational effort.

cs.LG↗

arXiv2021

Using a Collated Cybersecurity Dataset for Machine Learning and Artificial Intelligence

Artificial Intelligence (AI) and Machine Learning (ML) algorithms can support the span of indicator-level, e.g. anomaly detection, to behavioral level cyber security modeling and inference. This contribution is based on a dataset named BRON which is amalgamated from public threat and vulnerability behavioral sources. We demonstrate how BRON can support prediction of related threat techniques and attack patterns. We also discuss other AI and ML uses of BRON to exploit its behavioral knowledge.

cs.CR↗

arXiv2021

Fostering Diversity in Spatial Evolutionary Generative Adversarial Networks

Generative adversary networks (GANs) suffer from training pathologies such as instability and mode collapse, which mainly arise from a lack of diversity in their adversarial interactions. Co-evolutionary GAN (CoE-GAN) training algorithms have shown to be resilient to these pathologies. This article introduces Mustangs, a spatially distributed CoE-GAN, which fosters diversity by using different loss functions during the training. Experimental analysis on MNIST and CelebA demonstrated that Mustangs trains statistically more accurate generators.

cs.LG↗

arXiv2021

Automating Cyber Threat Hunting Using NLP, Automated Query Generation, and Genetic Perturbation

Scaling the cyber hunt problem poses several key technical challenges. Detecting and characterizing cyber threats at scale in large enterprise networks is hard because of the vast quantity and complexity of the data that must be analyzed as adversaries deploy varied and evolving tactics to accomplish their goals. There is a great need to automate all aspects, and, indeed, the workflow of cyber hunting. AI offers many ways to support this. We have developed the WILEE system that automates cyber threat hunting by translating high-level threat descriptions into many possible concrete implementations. Both the (high-level) abstract and (low-level) concrete implementations are represented using a custom domain specific language (DSL). WILEE uses the implementations along with other logic, also written in the DSL, to automatically generate queries to confirm (or refute) any hypotheses tied to the potential adversarial workflows represented at various layers of abstraction.

cs.CR↗

arXiv2021

Generating Adversarial Computer Programs using Optimized Obfuscations

Machine learning (ML) models that learn and predict properties of computer programs are increasingly being adopted and deployed. These models have demonstrated success in applications such as auto-completing code, summarizing large programs, and detecting bugs and malware in programs. In this work, we investigate principled ways to adversarially perturb a computer program to fool such learned models, and thus determine their adversarial robustness. We use program obfuscations, which have conventionally been used to avoid attempts at reverse engineering programs, as adversarial perturbations. These perturbations modify programs in ways that do not alter their functionality but can be crafted to deceive an ML model when making a decision. We provide a general formulation for an adversarial program that allows applying multiple obfuscation transformations to a program in any language. We develop first-order optimization algorithms to efficiently determine two key aspects -- which parts of the program to transform, and what transformations to use. We show that it is important to optimize both these aspects to generate the best adversarially perturbed program. Due to the discrete nature of this problem, we also propose using randomized smoothing to improve the attack loss landscape to ease optimization. We evaluate our work on Python and Java programs on the problem of program summarization. We show that our best attack proposal achieves a $52\%$ improvement over a state-of-the-art attack generation approach for programs trained on a seq2seq model. We further show that our formulation is better at training models that are robust to adversarial attacks.

cs.LG↗

arXiv2021

Linking Threat Tactics, Techniques, and Patterns with Defensive Weaknesses, Vulnerabilities and Affected Platform Configurations for Cyber Hunting

Many public sources of cyber threat and vulnerability information exist to help defend cyber systems. This paper links MITRE's ATT&CK MATRIX of Tactics and Techniques, NIST's Common Weakness Enumerations (CWE), Common Vulnerabilities and Exposures (CVE), and Common Attack Pattern Enumeration and Classification list (CAPEC), to gain further insight from alerts, threats and vulnerabilities. We preserve all entries and relations of the sources, while enabling bi-directional, relational path tracing within an aggregate data graph called BRON. In one example, we use BRON to enhance the information derived from a list of the top 10 most frequently exploited CVEs. We identify attack patterns, tactics, and techniques that exploit these CVEs and also uncover a disparity in how much linked information exists for each of these CVEs. This prompts us to further inventory BRON's collection of sources to provide a view of the extent and range of the coverage and blind spots of public data sources.

cs.CR↗

arXiv2021

Signal Propagation in a Gradient-Based and Evolutionary Learning System

Generative adversarial networks (GANs) exhibit training pathologies that can lead to convergence-related degenerative behaviors, whereas spatially-distributed, coevolutionary algorithms (CEAs) for GAN training, e.g. Lipizzaner, are empirically robust to them. The robustness arises from diversity that occurs by training populations of generators and discriminators in each cell of a toroidal grid. Communication, where signals in the form of parameters of the best GAN in a cell propagate in four directions: North, South, West, and East, also plays a role, by communicating adaptations that are both new and fit. We propose Lipi-Ring, a distributed CEA like Lipizzaner, except that it uses a different spatial topology, i.e. a ring. Our central question is whether the different directionality of signal propagation (effectively migration to one or more neighbors on each side of a cell) meets or exceeds the performance quality and training efficiency of Lipizzaner Experimental analysis on different datasets (i.e, MNIST, CelebA, and COVID-19 chest X-ray images) shows that there are no significant differences between the performances of the trained generative models by both methods. However, Lipi-Ring significantly reduces the computational time (14.2%. . . 41.2%). Thus, Lipi-Ring offers an alternative to Lipizzaner when the computational cost of training matters.

cs.NE↗

arXiv2020

Parallel/distributed implementation of cellular training for generative adversarial neural networks

Generative adversarial networks (GANs) are widely used to learn generative models. GANs consist of two networks, a generator and a discriminator, that apply adversarial learning to optimize their parameters. This article presents a parallel/distributed implementation of a cellular competitive coevolutionary method to train two populations of GANs. A distributed memory parallel implementation is proposed for execution in high performance/supercomputing centers. Efficient results are reported on addressing the generation of handwritten digits (MNIST dataset samples). Moreover, the proposed implementation is able to reduce the training times and scale properly when considering different grid sizes for training.

cs.DC↗