arXiv subjects

Diksha Goel

Publications and source records attributed to Diksha Goel.

At least 19 recordsLinked to original sources

arXiv2026

CausalNav: Reliability-Certified Causal World Models for Control under Physical-Parameter Shift

A world model is only useful for physical AI if it changes what the agent does, and only safe if it declines to do so when it is wrong. We study both halves of that requirement with CausalNav, a controller built around a signed, action-conditioned transition graph over identified state coordinates. At deployment CausalNav simulates a small library of intervention sequences, converts their objective error into policy-logit advice, and admits that advice only when a scale-free predictive-reliability certificate, a policy-margin gate, and an argmax-agreement gate all pass; otherwise it falls back exactly to its own model-based base controller. We evaluate against nine controlled baselines (transformer, recurrent, split-latent, graph, causal-induction, and three recent model-based reasoning modules) on CartPole-v1 and discretized Pendulum-v1 with physical-parameter shifts, under one shared PPO trainer, one interaction budget, and ten held-out seeds (200 runs). CausalNav attains the best average rank (1.25 of ten). The diagnostic result is more informative than the ranking: the learned graph recovers structure well above chance (CartPole F1 = 0.59 +/- 0.09), yet per-seed structural fidelity is uncorrelated with per-seed control benefit (r = -0.15, p = 0.67), and the certificate abstains on 10/10 Pendulum seeds, where forcing the planner on costs return. Model fidelity did not predict downstream control utility in our setting; certified abstention, not better prediction, is what made the world model safe to deploy.

cs.AI↗

arXiv2026

When the Judge Should Not Decide: Evidence-Locked, Non-Compensatory Selection Bounds LLM-Judge Failure in Reasoning Pipelines

An LLM judge deployed inside a reasoning pipeline does not merely measure quality, it decides which answer ships. We show that the cost of that decision depends less on judge accuracy than on the decision rule the judge is embedded in. On frozen candidate pools from four GRPO policies, an unconstrained scalar DeepSeek-R1-7B judge buys almost nothing over answer-level majority vote (+1.0 pp on 500 GSM8K questions, +0.34 EM on 300 HotpotQA questions), and on a frozen-rule 30-question confirmation split it is 10 points worse than majority, a judge that destroys accuracy while scoring candidates confidently. We then subordinate the same judge to Evidence-Locked Derive-Gate-Repair (EL-DGR), a task-adaptive non-compensatory rule under which a judge preference may override evidence-supported consensus only with an extractive evidence certificate, and a repair only when neither alternative is certified and the repair is. With no change to the judge, the candidates, or the budget, EL-DGR reaches 58.2% on GSM8K (vs. 56.8% judge, 55.8% majority, 55.4% first candidate) and 17.33 EM / 25.46 F1 on HotpotQA (vs. 15.67/23.49, 15.33/23.19, 15.33/22.97), improving on first-candidate GRPO by +2.8 pp (exact McNemar p=0.0026) and +2.00 EM (p=0.070, borderline). A decision audit shows why: EL-DGR overturns consensus on only 8 of 30 pilot questions and never converts a correct consensus into an incorrect answer. We also report what did not work: the same seven-channel decomposition used as a step-level gated training reward is null, and corrected channel-drop ablations show no channel is individually necessary (p=1.0 throughout). The practitioner-facing finding is negative about judges and positive about admissibility, bound the judge's blast radius rather than trying to make it accurate.

cs.AI↗

arXiv2026

DEFENGRAPH: Knowledge Graph-Enhanced LLMs for Blue Team Cyber Defense

Large Language Models (LLMs) show promise for supporting decision-making in cybersecurity, but their reliability in high-stakes, time-evolving environments remains limited due to hallucinations, poor temporal reasoning, and shallow grounding in system context. We introduce DEFENGRAPH, an LLM-driven assistant designed to support human defenders during cybersecurity incidents. DEFENGRAPH improves contextual reasoning by integrating a dual-layer Static-Dynamic Knowledge Graph (KG) with graph-based path retrieval, LLM-driven contextual filtering, and reasoning-based re-ranking. The framework grounds LLM outputs in both long-term domain knowledge and evolving event context, enabling faithful and temporally aware decision support. We evaluate DEFENGRAPH in a cyber defense setting using knowledge graphs constructed from heterogeneous security artifacts, including SIEM alerts, system topology, attacker behaviors, and prior defensive actions. The evaluation uses data collected during live Red vs. Blue team cyber range exercises simulating attacks on critical infrastructure, which generate realistic and noisy datasets reflecting real-world defender workflows and system dynamics. Evaluations across four prevalent LLMs show that DEFENGRAPH sets a new state-of-the-art: on GPT-4o it boosts reasoning-recall from 61.45\% to 73.49\% and ticket-action recall from 52.17% to 72.46% (precision 24.49\% to 29.24\%), with similar gains on LLaMA-3 (46.99\% to 61.45\%), DeepSeek-R1 (45.78\% to 56.63\%) and QWen-3 (51.81\% to 59.04\%), while surfacing up to 50 correct defense actions versus 36 for the next best baseline and holding fault rates steady.

cs.CR↗

arXiv2026

AgenticVM: Agentic AI for Adaptive Software Vulnerability Management

As software systems grow in scale and complexity, vulnerability management is increasingly strained by high alert volumes, fragmented toolchains, and manual triage processes. We introduce AgenticVM, a multi-agent framework that integrates large language models with security tools to automate vulnerability detection, assessment, prioritization, and reporting. AgenticVM combines rule-based processing, a BERT-based CVSS prediction module, and specialised LLM-driven agents, leveraging data from sources such as the National Vulnerability Database and the European Union Vulnerability Database. Across multiple evaluation scenarios, AgenticVM reduces raw scanner outputs into compact, actionable queues, achieving up to 98% alert reduction (e.g., from 3,983 findings to 82 high-priority items), while predicting missing CVSS attributes with 89.3% accuracy. These results demonstrate improved prioritisation efficiency and reduced analyst workload without compromising risk visibility. Beyond performance, the framework provides practical design insights into agent decomposition, tool-LLM integration, and human-in-the-loop governance for real-world deployment.

cs.CR↗

arXiv2026

Explainable Autonomous Cyber Defense using Adversarial Multi-Agent Reinforcement Learning

Autonomous agents are increasingly deployed in both offensive and defensive cyber operations, creating high-speed, closed-loop interactions in critical infrastructure environments. Advanced Persistent Threat (APT) actors exploit "Living off the Land" techniques and targeted telemetry perturbations to induce ambiguity in monitoring systems, causing automated defenses to overreact or misclassify benign behavior as malicious activity. Existing monolithic and multi-agent defense pipelines largely operate on correlation-based signals, lack structural constraints on response actions, and are vulnerable to reasoning drift under ambiguous or adversarial inputs. We present the Causal Multi-Agent Decision Framework (C-MADF), a structurally constrained architecture for autonomous cyber defense that integrates causal modeling with adversarial dual-policy control. C-MADF first learns a Structural Causal Model (SCM) from historical telemetry and compiles it into an investigation-level Directed Acyclic Graph (DAG) that defines admissible response transitions. This roadmap is formalized as a Markov Decision Process (MDP) whose action space is explicitly restricted to causally consistent transitions. Decision-making within this constrained space is performed by a dual-agent reinforcement learning system in which a threat-optimizing Blue-Team policy is counterbalanced by a conservatively shaped Red-Team policy. Inter-policy disagreement is quantified through a Policy Divergence Score and exposed via a human-in-the-loop interface equipped with an Explainability-Transparency Score that serves as an escalation signal under uncertainty. On the real-world CICIoT2023 dataset, C-MADF reduces the false-positive rate from 11.2%, 9.7%, and 8.4% in three cutting-edge literature baselines to 1.8%, while achieving 0.997 precision, 0.961 recall, and 0.979 F1-score.

cs.CR↗

arXiv2026

TempoNet: Learning Realistic Communication and Timing Patterns for Network Traffic Simulation

Realistic network traffic simulation is critical for evaluating intrusion detection systems, stress-testing network protocols, and constructing high-fidelity environments for cybersecurity training. While attack traffic can often be layered into training environments using red-teaming or replay methods, generating authentic benign background traffic remains a core challenge -- particularly in simulating the complex temporal and communication dynamics of real-world networks. This paper introduces TempoNet, a novel generative model that combines multi-task learning with multi-mark temporal point processes to jointly model inter-arrival times and all packet- and flow-header fields. TempoNet captures fine-grained timing patterns and higher-order correlations such as host-pair behavior and seasonal trends, addressing key limitations of GAN-, LLM-, and Bayesian-based methods that fail to reproduce structured temporal variation. TempoNet produces temporally consistent, high-fidelity traces, validated on real-world datasets. Furthermore, we show that intrusion detection models trained on TempoNet-generated background traffic perform comparably to those trained on real data, validating its utility for real-world security applications.

cs.CR↗

arXiv2025

3S-Trader: A Multi-LLM Framework for Adaptive Stock Scoring, Strategy, and Selection in Portfolio Optimization

Large Language Models (LLMs) have recently gained popularity in stock trading for their ability to process multimodal financial data. However, most existing methods focus on single-stock trading and lack the capacity to reason over multiple candidates for portfolio construction. Moreover, they typically lack the flexibility to revise their strategies in response to market shifts, limiting their adaptability in real-world trading. To address these challenges, we propose 3S-Trader, a training-free framework that incorporates scoring, strategy, and selection modules for stock portfolio construction. The scoring module summarizes each stock's recent signals into a concise report covering multiple scoring dimensions, enabling efficient comparison across candidates. The strategy module analyzes historical strategies and overall market conditions to iteratively generate an optimized selection strategy. Based on this strategy, the selection module identifies and assembles a portfolio by choosing stocks with higher scores in relevant dimensions. We evaluate our framework across four distinct stock universes, including the Dow Jones Industrial Average (DJIA) constituents and three sector-specific stock sets. Compared with existing multi-LLM frameworks and time-series-based baselines, 3S-Trader achieves the highest accumulated return of 131.83% on DJIA constituents with a Sharpe ratio of 0.31 and Calmar ratio of 11.84, while also delivering consistently strong results across other sectors.

q-fin.PM↗

arXiv2025

RegimeFolio: A Regime Aware ML System for Sectoral Portfolio Optimization in Dynamic Markets

Financial markets are inherently non-stationary, with shifting volatility regimes that alter asset co-movements and return distributions. Standard portfolio optimization methods, typically built on stationarity or regime-agnostic assumptions, struggle to adapt to such changes. To address these challenges, we propose RegimeFolio, a novel regime-aware and sector-specialized framework that, unlike existing regime-agnostic models such as DeepVol and DRL optimizers, integrates explicit volatility regime segmentation with sector-specific ensemble forecasting and adaptive mean-variance allocation. This modular architecture ensures forecasts and portfolio decisions remain aligned with current market conditions, enhancing robustness and interpretability in dynamic markets. RegimeFolio combines three components: (i) an interpretable VIX-based classifier for market regime detection; (ii) regime and sector-specific ensemble learners (Random Forest, Gradient Boosting) to capture conditional return structures; and (iii) a dynamic mean-variance optimizer with shrinkage-regularized covariance estimates for regime-aware allocation. We evaluate RegimeFolio on 34 large cap U.S. equities from 2020 to 2024. The framework achieves a cumulative return of 137 percent, a Sharpe ratio of 1.17, a 12 percent lower maximum drawdown, and a 15 to 20 percent improvement in forecast accuracy compared to conventional and advanced machine learning benchmarks. These results show that explicitly modeling volatility regimes in predictive learning and portfolio allocation enhances robustness and leads to more dependable decision-making in real markets.

q-fin.PM↗

arXiv2025

From Promise to Peril: Rethinking Cybersecurity Red and Blue Teaming in the Age of LLMs

Large Language Models (LLMs) are set to reshape cybersecurity by augmenting red and blue team operations. Red teams can exploit LLMs to plan attacks, craft phishing content, simulate adversaries, and generate exploit code. Conversely, blue teams may deploy them for threat intelligence synthesis, root cause analysis, and streamlined documentation. This dual capability introduces both transformative potential and serious risks. This position paper maps LLM applications across cybersecurity frameworks such as MITRE ATT&CK and the NIST Cybersecurity Framework (CSF), offering a structured view of their current utility and limitations. While LLMs demonstrate fluency and versatility across various tasks, they remain fragile in high-stakes, context-heavy environments. Key limitations include hallucinations, limited context retention, poor reasoning, and sensitivity to prompts, which undermine their reliability in operational settings. Moreover, real-world integration raises concerns around dual-use risks, adversarial misuse, and diminished human oversight. Malicious actors could exploit LLMs to automate reconnaissance, obscure attack vectors, and lower the technical threshold for executing sophisticated attacks. To ensure safer adoption, we recommend maintaining human-in-the-loop oversight, enhancing model explainability, integrating privacy-preserving mechanisms, and building systems robust to adversarial exploitation. As organizations increasingly adopt AI driven cybersecurity, a nuanced understanding of LLMs' risks and operational impacts is critical to securing their defensive value while mitigating unintended consequences.

cs.CR↗

arXiv2025

Unveiling the Black Box: A Multi-Layer Framework for Explaining Reinforcement Learning-Based Cyber Agents

Reinforcement Learning (RL) agents are increasingly used to simulate sophisticated cyberattacks, but their decision-making processes remain opaque, hindering trust, debugging, and defensive preparedness. In high-stakes cybersecurity contexts, explainability is essential for understanding how adversarial strategies are formed and evolve over time. In this paper, we propose a unified, multi-layer explainability framework for RL-based attacker agents that reveals both strategic (Markov Decision Process (MDP)-level) and tactical (policy-level) reasoning. At the MDP-level, we model cyberattacks as a Partially Observable Markov Decision Process (POMDP) to expose exploration-exploitation dynamics and phase-aware behavioural shifts. At the policy-level, we analyse the temporal evolution of Q-values and use Prioritised Experience Replay (PER) to surface critical learning transitions and evolving action preferences. Evaluated across CyberBattleSim environments of increasing complexity, our framework offers interpretable insights into agent behaviour at scale. Unlike previous explainable RL methods, which are {predominantly} post-hoc, domain-specific, or limited in depth, our approach is both agent- and environment-agnostic, {supporting use cases such as red-team simulation, RL policy debugging, phase-aware threat modelling and anticipatory defence planning.} By transforming black-box learning into actionable behavioural intelligence, our framework enables both defenders and developers to better anticipate, analyse, and respond to autonomous cyber threats.

cs.CR↗

arXiv2025

Co-Evolutionary Defence of Active Directory Attack Graphs via GNN-Approximated Dynamic Programming

Modern enterprise networks increasingly rely on Active Directory (AD) for identity and access management. However, this centralization exposes a single point of failure, allowing adversaries to compromise high-value assets. Existing AD defense approaches often assume static attacker behavior, but real-world adversaries adapt dynamically, rendering such methods brittle. To address this, we model attacker-defender interactions in AD as a Stackelberg game between an adaptive attacker and a proactive defender. We propose a co-evolutionary defense framework that combines Graph Neural Network Approximated Dynamic Programming (GNNDP) to model attacker strategies, with Evolutionary Diversity Optimization (EDO) to generate resilient blocking strategies. To ensure scalability, we introduce a Fixed-Parameter Tractable (FPT) graph reduction method that reduces complexity while preserving strategic structure. Our framework jointly refines attacker and defender policies to improve generalization and prevent premature convergence. Experiments on synthetic AD graphs show near-optimal results (within 0.1 percent of optimality on r500) and improved performance on larger graphs (r1000 and r2000), demonstrating the framework's scalability and effectiveness.

cs.CR↗

arXiv2025

CyberAlly: Leveraging LLMs and Knowledge Graphs to Empower Cyber Defenders

The increasing frequency and sophistication of cyberattacks demand innovative approaches to strengthen defense capabilities. Training on live infrastructure poses significant risks to organizations, making secure, isolated cyber ranges an essential tool for conducting Red vs. Blue Team training events. These events enable security teams to refine their skills without impacting operational environments. While such training provides a strong foundation, the ever-evolving nature of cyber threats necessitates additional support for effective defense. To address this challenge, we introduce CyberAlly, a knowledge graph-enhanced AI assistant designed to enhance the efficiency and effectiveness of Blue Teams during incident response. Integrated into our cyber range alongside an open-source SIEM platform, CyberAlly monitors alerts, tracks Blue Team actions, and suggests tailored mitigation recommendations based on insights from prior Red vs. Blue Team exercises. This demonstration highlights the feasibility and impact of CyberAlly in augmenting incident response and equipping defenders to tackle evolving threats with greater precision and confidence.

cs.CR↗

arXiv2025

Maintenance of Structural Hole Spanners in Dynamic Networks

Structural Hole (SH) spanners are the set of users who bridge different groups of users and are vital in numerous applications. Despite their importance, existing work for identifying SH spanners focuses only on static networks. However, real-world networks are highly dynamic where the underlying structure of the network evolves continuously. Consequently, we study SH spanner problem for dynamic networks. We propose an efficient solution for updating SH spanners in dynamic networks. Our solution reuses the information obtained during the initial runs of the static algorithm and avoids the recomputations for the nodes unaffected by the updates. Experimental results show that the proposed solution achieves a minimum speedup of 3.24 over recomputation. To the best of our knowledge, this is the first attempt to address the problem of maintaining SH spanners in dynamic networks.

cs.SI↗

arXiv2025

CAMP in the Odyssey: Provably Robust Reinforcement Learning with Certified Radius Maximization

Deep reinforcement learning (DRL) has gained widespread adoption in control and decision-making tasks due to its strong performance in dynamic environments. However, DRL agents are vulnerable to noisy observations and adversarial attacks, and concerns about the adversarial robustness of DRL systems have emerged. Recent efforts have focused on addressing these robustness issues by establishing rigorous theoretical guarantees for the returns achieved by DRL agents in adversarial settings. Among these approaches, policy smoothing has proven to be an effective and scalable method for certifying the robustness of DRL agents. Nevertheless, existing certifiably robust DRL relies on policies trained with simple Gaussian augmentations, resulting in a suboptimal trade-off between certified robustness and certified return. To address this issue, we introduce a novel paradigm dubbed \texttt{C}ertified-r\texttt{A}dius-\texttt{M}aximizing \texttt{P}olicy (\texttt{CAMP}) training. \texttt{CAMP} is designed to enhance DRL policies, achieving better utility without compromising provable robustness. By leveraging the insight that the global certified radius can be derived from local certified radii based on training-time statistics, \texttt{CAMP} formulates a surrogate loss related to the local certified radius and optimizes the policy guided by this surrogate loss. We also introduce \textit{policy imitation} as a novel technique to stabilize \texttt{CAMP} training. Experimental results demonstrate that \texttt{CAMP} significantly improves the robustness-return trade-off across various tasks. Based on the results, \texttt{CAMP} can achieve up to twice the certified expected return compared to that of baselines. Our code is available at https://github.com/NeuralSec/camp-robust-rl.

cs.LG↗

arXiv2025

The Future of AI: Exploring the Potential of Large Concept Models

The field of Artificial Intelligence (AI) continues to drive transformative innovations, with significant progress in conversational interfaces, autonomous vehicles, and intelligent content creation. Since the launch of ChatGPT in late 2022, the rise of Generative AI has marked a pivotal era, with the term Large Language Models (LLMs) becoming a ubiquitous part of daily life. LLMs have demonstrated exceptional capabilities in tasks such as text summarization, code generation, and creative writing. However, these models are inherently limited by their token-level processing, which restricts their ability to perform abstract reasoning, conceptual understanding, and efficient generation of long-form content. To address these limitations, Meta has introduced Large Concept Models (LCMs), representing a significant shift from traditional token-based frameworks. LCMs use concepts as foundational units of understanding, enabling more sophisticated semantic reasoning and context-aware decision-making. Given the limited academic research on this emerging technology, our study aims to bridge the knowledge gap by collecting, analyzing, and synthesizing existing grey literature to provide a comprehensive understanding of LCMs. Specifically, we (i) identify and describe the features that distinguish LCMs from LLMs, (ii) explore potential applications of LCMs across multiple domains, and (iii) propose future research directions and practical strategies to advance LCM development and adoption.

cs.CL↗

arXiv2024

Detection and Prevention of Smishing Attacks

Phishing is an online identity theft technique where attackers steal users personal information, leading to financial losses for individuals and organizations. With the increasing adoption of smartphones, which provide functionalities similar to desktop computers, attackers are targeting mobile users. Smishing, a phishing attack carried out through Short Messaging Service (SMS), has become prevalent due to the widespread use of SMS-based services. It involves deceptive messages designed to extract sensitive information. Despite the growing number of smishing attacks, limited research focuses on detecting these threats. This work presents a smishing detection model using a content-based analysis approach. To address the challenge posed by slang, abbreviations, and short forms in text communication, the model normalizes these into standard forms. A machine learning classifier is employed to classify messages as smishing or ham. Experimental results demonstrate the model effectiveness, achieving classification accuracies of 97.14% for smishing and 96.12% for ham messages, with an overall accuracy of 96.20%.

cs.CR↗

arXiv2024

Machine Learning Driven Smishing Detection Framework for Mobile Security

The increasing reliance on smartphones for communication, financial transactions, and personal data management has made them prime targets for cyberattacks, particularly smishing, a sophisticated variant of phishing conducted via SMS. Despite the growing threat, traditional detection methods often struggle with the informal and evolving nature of SMS language, which includes abbreviations, slang, and short forms. This paper presents an enhanced content-based smishing detection framework that leverages advanced text normalization techniques to improve detection accuracy. By converting nonstandard text into its standardized form, the proposed model enhances the efficacy of machine learning classifiers, particularly the Naive Bayesian classifier, in distinguishing smishing messages from legitimate ones. Our experimental results, validated on a publicly available dataset, demonstrate a detection accuracy of 96.2%, with a low False Positive Rate of 3.87% and False Negative Rate of 2.85%. This approach significantly outperforms existing methodologies, providing a robust solution to the increasingly sophisticated threat of smishing in the mobile environment.

cs.CR↗

arXiv2024

ChatNVD: Advancing Cybersecurity Vulnerability Assessment with Large Language Models

The increasing frequency and sophistication of cybersecurity vulnerabilities in software systems underscores the need for more robust and effective vulnerability assessment methods. However, existing approaches often rely on highly technical and abstract frameworks, which hinder understanding and increase the likelihood of exploitation, resulting in severe cyberattacks. In this paper, we introduce ChatNVD, a support tool powered by Large Language Models (LLMs) that leverages the National Vulnerability Database (NVD) to generate accessible, context-rich summaries of software vulnerabilities. We develop three variants of ChatNVD, utilizing three prominent LLMs: GPT-4o Mini by OpenAI, LLaMA 3 by Meta, and Gemini 1.5 Pro by Google. To evaluate their performance, we conduct a comparative evaluation focused on their ability to identify, interpret, and explain software vulnerabilities. Our results demonstrate that GPT-4o Mini outperforms the other models, achieving over 92% accuracy and the lowest error rates, making it the most reliable option for real-world vulnerability assessment.

cs.CR↗