Searcharxiv⌕ Search

arXiv subjects

Shaswata Mitra

Publications and source records attributed to Shaswata Mitra.

At least 19 recordsLinked to original sources

Where Rules End and Judges Begin: Measuring the Judgment Boundary in Multi-Agent Systems Security

LLM-based multi-agent systems (MAS) engage tools, share memory, and delegate tasks, often encountering adversarial content. Current defenses for MAS are typically evaluated in isolation, focusing on one attack type at a time, which can lead to costly and hard-to-audit outcomes. This study organizes defenses into five principles, implementing them as DEFER1 (DEterministic-First Enforcement with Residual judgment), which includes a cascade of 28 checks that blocks what it can and refers the rest to a panel of four judges. In independent testing across four domains, attack success rates drop from about 30.0% to approximately 3.0%, with 78% of blocked attacks handled by deterministic checks. Only a quarter of proposals reach the judges in the security-operations domain, illustrating that the rules provide security for attacks violating clear policies, while judges manage those that only misrepresent intent. Both systems have weaknesses, such as a risk-score approval gate that inaccurately approves most attack proposals but few legitimate ones, highlighting the challenges in assessing threats accurately.

cs.AI↗

The Value of Spike Timing: A Leakage-Resistant Benchmark of SNN Design Choices for Network Intrusion Detection

Spiking neural networks (SNNs) are increasingly studied for network intrusion detection, but comparative evidence on how neuron models and spike encodings affect performance remains limited. Evaluation choices can further influence the observed results when preprocessing, capture structure, or scenario information crosses the train-test boundary. We evaluate nine snnTorch neuron families with three spike encodings, yielding 27 SNN configurations across four intrusion-detection benchmarks. We first screen the complete design space and then repeat the evaluation using train-only transforms, seed-independent partitions, and capture- or scenario-aware separation. At the shared operating point, LeakyParallel/latency achieved the lowest mean rank in both sweeps but was not statistically separated from Leaky/latency; their screening order reversed when CTU-13 was excluded. Overall, screening and confirmation retained substantial rank agreement despite changes in measured performance. We then examine what latency coding contributes by holding the active spike set fixed and changing only its temporal organization. At the main T=25 operating point, mapping feature magnitude to spike time improved macro-F1 on all five confirmation protocols, while spreading the same spikes through time without that mapping could either improve or reduce performance. Latency coding thus combines informative spike timing with temporal network dynamics. Sparse input encoding does not directly imply sparse internal activity, although latency coding requires fewer fanout-weighted operations than rate coding in the evaluated models. These findings motivate separate assessment of SNN design, evaluation protocol, spike timing, and computational activity for static network-flow data.

cs.CR↗

Staying on the Attractor: Supervising Neural Surrogates of 3D Turbulence Where They Leave It

Neural surrogates are trained to predict 3D turbulent flows in place of direct numerical simulation (DNS). For chaotic flows, the goal is short-term pointwise accuracy followed by long-term physical and statistical fidelity. However, small prediction errors can carry a surrogate away from the flow's attractor. Off-attractor states are poorly represented in training data, leaving their evolution weakly constrained. The learned dynamics can then amplify deviations and lead to blow-up, freezing, or statistical drift. We propose off-attractor supervision (OAS) to supervise neural surrogates where they leave the attractor. OAS teaches the model how the true Navier-Stokes dynamics would evolve from these states. Each selected state is paired with its own future computed by DNS. Three generators select a few hundred states for relabeling. The first collects states from the surrogate's own rollouts. The second uses surrogate attacks to target freezing, excessive amplification, and violations of incompressibility and energy balance. The third perturbs training states along an amplified direction and a strongly damped random direction of the dynamics. All attacks run on the surrogate alone, and DNS relabeling is performed offline once per selected state. Experiments on $128^3$ turbulence show that OAS increases the median time to failure from 21 to 721 steps. The compared baselines achieve medians of at most 110 steps, and the advantage holds across training seeds. OAS also achieves the lowest pointwise error at step 15 and the best long-horizon statistics among the compared methods. OAS integrates physical models into neural simulation by extending supervision from fixed reference trajectories to states where the surrogate is likely to fail. This principle can guide the development of more reliable scientific surrogates when deployment takes models beyond the coverage of their training data.

cs.LG↗

Evaluating the NIST Bugs Framework Against CWE as a Successor for Automated Vulnerability Classification

Vulnerability classification based on root cause weaknesses is essential for numerous cybersecurity activities, where the Common Weakness Enumeration (CWE) serves as a public repository of such flaws. However, its overlapping entries create a non-orthogonal structure. The result is the same vulnerability being mapped to multiple weaknesses, complicating Root Cause Analysis (RCA) and triage. To address this, NIST Special Publication 800-231 introduces the Bugs Framework (BF), which organizes vulnerabilities into triples and links such triples into a causal chain, so that a vulnerability carries its root cause and its sink together instead of a single terminal label. To date, however, BF has been specified but not evaluated regarding its performance against the challenges to automated classification. The evidence required for adoption has not been investigated empirically. We evaluate BF as a classification target and a complement to CWE using a systematically screened corpus of automated Common Vulnerabilities and Exposures (CVEs) linked to CWE research. We assess the reproducibility of CVE-to-BF classification through two evaluations. The first is qualitative: an anonymized inter-rater study in which 2 subject-matter experts (SMEs) independently mapped 13 CVEs onto the four BF axes. Annotators showed strong agreement on the cause and operation axes, while the attribute axis indicated fair agreement. We also tested our automated framework across two large language model (LLM) deployments under different budgets for reproducibility analysis. Despite limitations, such as evidence availability and the absence of retrievable fix commits for closed-source software, our findings support the claim that BF is a more structured and automation-friendly framework than CWE. Our exploration reveals specific gaps in BF, including under-specified guidance on attributes.

cs.CR↗

Gated Activation Steering for Reducing Sycophancy & Hallucination in Medical Question Answering

Sycophancy and hallucination are persistent failure modes of Large Language Models (LLMs) across domains. However, it becomes particularly consequential in clinical question answering, where responses must remain grounded in the provided context and robust to user pressure. Hallucination can introduce information that is unsupported by the context, while sycophancy can cause a model to abandon a previously correct answer when challenged by the user. Existing approaches, such as prompt-based safeguards and always-on activation steering, often address these behaviors separately or apply interventions broadly across turns, which can unnecessarily deteriorate responses that were already correct. To address these limitations within a single framework, we employ Inference Time Intervention (ITI) to jointly control both behaviors by learning separate steering directions for hallucination and sycophancy from contrastive clinical pairs and applying them to causally verified attention heads. During runtime, behavior-specific gates then determine when intervention is needed: the hallucination component mitigates unsupported claims, while the sycophancy component mitigates answer shifts caused by user pressure. We evaluate this framework on clinical questions grounded in EHR data while keeping the model weights frozen. Across all evaluation settings, we conducted 15,900 model-response runs. Across 600 pressure trajectories for the 4-billion-parameter model, the unsteered model caved in 570 cases. At the same time, gated steering helped it last longer in 551 of them. It held its ground under pressure at levels comparable to those of models with more than 100 billion parameters, showing that targeted inference-time steering can improve robustness without intervening at every turn.

cs.AI↗

Find Before You Fine-Tune: A Diagnostic Study of Small LLMs for Cybersecurity QA

Large Language Models (LLMs) are increasingly fine-tuned for critical-domain Question-Answering (QA), yet choosing which small model to adapt, before paying the cost of adaptation, remains difficult. Fine-tuning can improve domain alignment, but it may also erode prior knowledge, weaken instruction-following, or increase hallucination, especially when labeled data are scarce or rapidly evolving as in cybersecurity. We present FiT (Find before Fine-Tune), a task-oriented diagnostic framework that characterizes small LLMs along three capabilities required for cybersecurity QA: vocabulary recognition, parametric knowledge, and contextualization of retrieved information. Using FiT, we conduct an empirical study of five open-weight 7-billion-parameter models under two fine-tuning regimes. We find that fine-tuning does not uniformly help: it consistently degrades vocabulary and parametric knowledge in small models, and the two regimes trade off differently. Knowledge-focused tuning causes moderate, rank-preserving degradation, whereas instruction-focused tuning collapses measured knowledge through induced abstention, inverting the knowledge ranking while leaving retrieval-grounded contextualization essentially intact. We quantify these regime-specific patterns with rank-correlation analysis and show that pre-fine-tuning FiT scores anticipate the direction of post-tuning change. Our results suggest that task-oriented diagnosis can screen out unsuitable models, avoid unnecessary fine-tuning, and support safer deployment of small LLMs in cybersecurity QA pipelines.

cs.CL↗

FALCON: Transforming Cyber Threat Intelligence into Deployable IDS Rules with Self-Reflection

Signature-based Intrusion Detection Systems (IDS) detect malicious activity by matching network or host events against predefined rules. Security analysts manually develop these rules from Cyber Threat Intelligence (CTI). As threats evolve, this manual pipeline faces two bottlenecks. Before authoring a new rule, an analyst must reconcile the incoming CTI with the existing rule base and determine whether to create, update, or retire one. This process is challenging due to the representational differences between the CTI and Rule formats. This gap limits the effectiveness of keyword- and embedding-based search, making rule reconciliation cognitively demanding and, in turn, contributing to "rule bloat". Second, automated verification of a new rule is inherently difficult as zero-day threats lack ground truth from simulated testing. Hence, standard metrics cannot prove that a rule semantically adheres to the CTI, and the use of LLMs leads to non-deterministic behavior. To address these challenges, we introduce FALCON, an agentic framework for CTI-grounded rule retrieval, generation, and validation. At its core, a novel CTI-Rule semantic scorer, quantifies the functional alignment between a CTI and a rule; the same signal drives a retriever that surfaces relevant deployed rules and a ground-truth-free validator that scores generated ones. Around it, a generation pipeline produces deployable rules from CTI in real time and refines them through self-reflective syntactic, semantic, and performance validators. Across network (Snort) and host-based (YARA) platforms on a purpose-built CTI-Rule dataset, FALCON attains a mean relevance of 0.72 (approx), with 84% inter-rater agreement among cybersecurity analysts, underscoring the promise of real-time security automation.

cs.CR↗

Agentra: A Supervisable Multi-Agent Framework for Enterprise Intrusion Response

Enterprise intrusion response still depends on static playbooks and analyst-driven triage, creating delay between alert generation and containment. We present Agentra, a supervisable multi-agent Intrusion Response System (IRS) framework that converts alerts from IDS, EDR, and XDR platforms into structured incident response plans grounded in MITRE ATT&CK, MITRE D3FEND, and NIST CSF 2.0. Agentra decomposes response reasoning across role-scoped agents, validates proposed plans through a bounded Planner--Validator review loop, screens retrieved threat intelligence through a Moderator security gateway, gates actions through an Action Catalog and risk score, and records decisions in an append-only audit log. We evaluate Agentra against a static OASIS CACAO v2.0 cyber-playbook baseline on a 120-event corpus drawn from ThreatHunter-Playbook, Splunk BOTSv3, and DARPA OpTC. The strongest configuration improves FP-aware IRS F1 from 0.61 to 0.84 and restores the projected harmful-action rate to the static baseline level of 0.0% after Planner-only configurations introduce unsafe overreaction. These results indicate that multi-agent response planning can improve ontology-grounded IRS coverage while preserving analyst approval and auditability.

cs.CR↗

Evaluating Open-Source LLMs for Multi-Label ATT&CK Technique Classification on CTI Reports

Classifying Cyber Threat Intelligence (CTI) using MITRE Adversarial Tactics, Techniques, and Common Knowledge (ATT&CK) is essential for proactive defense, but historically required extensive human effort. Pre-Large Language Model (LLM) automation sped up this process, but could not resolve the complex language and multi-step attack patterns found in unstructured CTI reports. LLMs addressed previous limitations by using contextual reasoning to understand unstructured text. However, current evaluations rely on simplified, single-technique sentences that ignore the complexity of real-world CTI reports, which often leads to inflated performance results. Consequently, the baseline performance of open-source LLMs on complex unstructured CTI reports remains unevaluated. To address this gap, we constructed a ground-truth dataset of 2,076 human-annotated sentences (1,281 technique-positive, 795 negative) from 83 complex unstructured CTI reports. These sentences were mapped to 114 unique ATT&CK techniques using a six-phase annotation process, achieving \k{appa} = 0.68 inter-annotator agreement. Using this dataset, we evaluated seven open-source LLMs ranging from 8B to 236B parameters across prompt strategy and temperature configurations. The highest-performing LLM achieved a micro-averaged F1 score of 0.22, establishing the empirical baseline for multi-label ATT&CK classification on complex unstructured CTI. Parameter size showed a statistically significant positive correlation with F1 score. Prompt strategy and temperature produced no statistically significant gains across model configurations. These results indicate that current open-source LLMs are insufficient for production-grade ATT&CK classification. The dataset, benchmark, and findings provide a reproducible foundation for future CTI research.

cs.CR↗

What Are Adversaries Doing? Automating Tactics, Techniques, and Procedures Extraction: A Systematic Review

Adversaries continuously evolve their tactics, techniques, and procedures (TTPs) to achieve their objectives while evading detection, requiring defenders to continually update their understanding of adversary behavior. Prior research has proposed automated extraction of TTP-related intelligence from unstructured text and mapping it to structured knowledge bases, such as MITRE ATT&CK. However, existing work varies widely in extraction objectives, datasets, modeling approaches, and evaluation practices, making it difficult to understand the research landscape. The goal of this study is to aid security researchers in understanding the state of the art in extracting attack tactics, techniques, and procedures (TTPs) from unstructured text by analyzing relevant literature. We systematically analyze 80 peer-reviewed studies across key dimensions: extraction purposes, data sources, dataset construction, modeling approaches, evaluation metrics, and artifact availability. Our analysis reveals several dominant trends. Technique-level classification remains the dominant task formulation, while tactic classification and technique searching are underexplored. The field has progressed from rule-based and traditional machine learning to transformer-based architectures (e.g., BERT, SecureBERT, RoBERTa), with recent studies exploring LLM-based approaches including prompting, retrieval-augmented generation, and fine-tuning, though adoption remains emergent. Despite these advances, important limitations persist: many studies rely on single-label classification, limited evaluation settings, and narrow datasets, constraining cross-domain generalization. Reproducibility is further hindered by proprietary datasets, limited code releases, and restricted corpora.

cs.SE↗

AgenticCyOps: Securing Multi-Agentic AI Integration in Enterprise Cyber Operations

Multi-agent systems (MAS) powered by LLMs promise adaptive, reasoning-driven enterprise workflows, yet granting agents autonomous control over tools, memory, and communication introduces attack surfaces absent from deterministic pipelines. While current research largely addresses prompt-level exploits and narrow individual vectors, it lacks a holistic architectural model for enterprise-grade security. We introduce AgenticCyOps (Securing Multi-Agentic AI Integration in Enterprise Cyber Operations), a framework built on a systematic decomposition of attack surfaces across component, coordination, and protocol layers, revealing that documented vectors consistently trace back to two integration surfaces: tool orchestration and memory management. Building on this observation, we formalize these integration surfaces as primary trust boundaries and define five defensive principles: authorized interfaces, capability scoping, verified execution, memory integrity & synchronization, and access-controlled data isolation; each aligned with established compliance standards (NIST, ISO 27001, GDPR, EU AI Act). We apply the framework to a Security Operations Center (SOC) workflow, adopting the Model Context Protocol (MCP) as the structural basis, with phase-scoped agents, consensus validation loops, and per-organization memory boundaries. Coverage analysis, attack path tracing, and trust boundary assessment confirm that the design addresses the documented attack vectors with defense-in-depth, intercepts three of four representative attack chains within the first two steps, and reduces exploitable trust boundaries by a minimum of 72% compared to a flat MAS, positioning AgenticCyOps as a foundation for securing enterprise-grade integration.

cs.CR↗

IRSDA: An Agent-Orchestrated Framework for Enterprise Intrusion Response

Modern enterprise systems face escalating cyber threats that are increasingly dynamic, distributed, and multi-stage in nature. Traditional intrusion detection and response systems often rely on static rules and manual workflows, which limit their ability to respond with the speed and precision required in high-stakes environments. To address these challenges, we present the Intrusion Response System Digital Assistant (IRSDA), an agent-based framework designed to deliver autonomous and policy-compliant cyber defense. IRSDA combines Self-Adaptive Autonomic Computing Systems (SA-ACS) with the Knowledge guided Monitor, Analyze, Plan, and Execute (MAPE-K) loop to support real-time, partition-aware decision-making across enterprise infrastructure. IRSDA incorporates a knowledge-driven architecture that integrates contextual information with AI-based reasoning to support system-guided intrusion response. The framework leverages retrieval mechanisms and structured representations to inform decision-making while maintaining alignment with operational policies. We assess the system using a representative real-world microservices application, demonstrating its ability to automate containment, enforce compliance, and provide traceable outputs for security analyst interpretation. This work outlines a modular and agent-driven approach to cyber defense that emphasizes explainability, system-state awareness, and operational control in intrusion response.

cs.CR↗

Semantic-Aware Contrastive Fine-Tuning: Boosting Multimodal Malware Classification with Discriminative Embeddings

The rapid evolution of malware variants requires robust classification methods to enhance cybersecurity. While Large Language Models (LLMs) offer potential for generating malware descriptions to aid family classification, their utility is limited by semantic embedding overlaps and misalignment with binary behavioral features. We propose a contrastive fine-tuning (CFT) method that refines LLM embeddings via targeted selection of hard negative samples based on cosine similarity, enabling LLMs to distinguish between closely related malware families. Our approach combines high-similarity negatives to enhance discriminative power and mid-tier negatives to increase embedding diversity, optimizing both precision and generalization. Evaluated on the CIC-AndMal-2020 and BODMAS datasets, our refined embeddings are integrated into a multimodal classifier within a Model-Agnostic Meta-Learning (MAML) framework on a few-shot setting. Experiments demonstrate significant improvements: our method achieves 63.15% classification accuracy with as few as 20 samples on CIC-AndMal-2020, outperforming baselines by 11--21 percentage points and surpassing prior negative sampling strategies. Ablation studies confirm the superiority of similarity-based selection over random sampling, with gains of 10-23%. Additionally, fine-tuned LLMs generate attribute-aware descriptions that generalize to unseen variants, bridging textual and binary feature gaps. This work advances malware classification by enabling nuanced semantic distinctions and provides a scalable framework for adapting LLMs to cybersecurity challenges.

cs.CR↗

LOCALINTEL: Generating Organizational Threat Intelligence from Global and Local Cyber Knowledge

Security Operations Center (SoC) analysts gather threat reports from openly accessible global threat repositories and tailor the information to their organization's needs, such as developing threat intelligence and security policies. They also depend on organizational internal repositories, which act as private local knowledge database. These local knowledge databases store credible cyber intelligence, critical operational and infrastructure details. SoCs undertake a manual labor-intensive task of utilizing these global threat repositories and local knowledge databases to create both organization-specific threat intelligence and mitigation policies. Recently, Large Language Models (LLMs) have shown the capability to process diverse knowledge sources efficiently. We leverage this ability to automate this organization-specific threat intelligence generation. We present LocalIntel, a novel automated threat intelligence contextualization framework that retrieves zero-day vulnerability reports from the global threat repositories and uses its local knowledge database to determine implications and mitigation strategies to alert and assist the SoC analyst. LocalIntel comprises two key phases: knowledge retrieval and contextualization. Quantitative and qualitative assessment has shown effectiveness in generating up to 93% accurate organizational threat intelligence with 64% inter-rater agreement.

cs.CR↗

CLINICSUM: Utilizing Language Models for Generating Clinical Summaries from Patient-Doctor Conversations

This paper presents ClinicSum, a novel framework designed to automatically generate clinical summaries from patient-doctor conversations. It utilizes a two-module architecture: a retrieval-based filtering module that extracts Subjective, Objective, Assessment, and Plan (SOAP) information from conversation transcripts, and an inference module powered by fine-tuned Pre-trained Language Models (PLMs), which leverage the extracted SOAP data to generate abstracted clinical summaries. To fine-tune the PLM, we created a training dataset of consisting 1,473 conversations-summaries pair by consolidating two publicly available datasets, FigShare and MTS-Dialog, with ground truth summaries validated by Subject Matter Experts (SMEs). ClinicSum's effectiveness is evaluated through both automatic metrics (e.g., ROUGE, BERTScore) and expert human assessments. Results show that ClinicSum outperforms state-of-the-art PLMs, demonstrating superior precision, recall, and F-1 scores in automatic evaluations and receiving high preference from SMEs in human assessment, making it a robust solution for automated clinical summarization.

cs.CL↗

IRSKG: Unified Intrusion Response System Knowledge Graph Ontology for Cyber Defense

Cyberattacks are becoming increasingly difficult to detect and prevent due to their sophistication. In response, Autonomous Intelligent Cyber-defense Agents (AICAs) are emerging as crucial solutions. One prominent AICA agent is the Intrusion Response System (IRS), which is critical for mitigating threats after detection. IRS uses several Tactics, Techniques, and Procedures (TTPs) to mitigate attacks and restore the infrastructure to normal operations. Continuous monitoring of the enterprise infrastructure is an essential TTP the IRS uses. However, each system serves different purposes to meet operational needs. Integrating these disparate sources for continuous monitoring increases pre-processing complexity and limits automation, eventually prolonging critical response time for attackers to exploit. We propose a unified IRS Knowledge Graph ontology (IRSKG) that streamlines the onboarding of new enterprise systems as a source for the AICAs. Our ontology can capture system monitoring logs and supplemental data, such as a rules repository containing the administrator-defined policies to dictate the IRS responses. Besides, our ontology permits us to incorporate dynamic changes to adapt to the evolving cyber-threat landscape. This robust yet concise design allows machine learning models to train effectively and recover a compromised system to its desired state autonomously with explainability.

cs.CR↗

Transfer Learning Applied to Computer Vision Problems: Survey on Current Progress, Limitations, and Opportunities

The field of Computer Vision (CV) has faced challenges. Initially, it relied on handcrafted features and rule-based algorithms, resulting in limited accuracy. The introduction of machine learning (ML) has brought progress, particularly Transfer Learning (TL), which addresses various CV problems by reusing pre-trained models. TL requires less data and computing while delivering nearly equal accuracy, making it a prominent technique in the CV landscape. Our research focuses on TL development and how CV applications use it to solve real-world problems. We discuss recent developments, limitations, and opportunities.

cs.CV↗

A Survey on Privacy Attacks Against Digital Twin Systems in AI-Robotics

Industry 4.0 has witnessed the rise of complex robots fueled by the integration of Artificial Intelligence/Machine Learning (AI/ML) and Digital Twin (DT) technologies. While these technologies offer numerous benefits, they also introduce potential privacy and security risks. This paper surveys privacy attacks targeting robots enabled by AI and DT models. Exfiltration and data leakage of ML models are discussed in addition to the potential extraction of models derived from first-principles (e.g., physics-based). We also discuss design considerations with DT-integrated robotics touching on the impact of ML model training, responsible AI and DT safeguards, data governance and ethical considerations on the effectiveness of these attacks. We advocate for a trusted autonomy approach, emphasizing the need to combine robotics, AI, and DT technologies with robust ethical frameworks and trustworthiness principles for secure and reliable AI robotic systems.

cs.RO↗