arXiv subjects

Sandeep K. Shukla

Publications and source records attributed to Sandeep K. Shukla.

10 recordsLinked to original sources

arXiv2026

How Do LLM Agents Actually Get the Flag? Trace-Level Provenance for Agentic Offensive Security Evaluation

Capture-the-Flag (CTF) benchmarks are widely used to assess the offensive security capabilities of autonomous language-model agents. Evaluations rely on shallow binary judgments or aggregate scores, overlooking the agent's trajectory to the flag. Consequently actual exploitation is conflated with direct flag exposure, memorized recall, external lookup, guessing, and unsupported claims, potentially overstating the agent's cybersecurity capability. We introduce CTF-ABACUS, a trace-based agent auditing framework that reconstructs each run as an evidence-grounded solve profile. By decomposing agent actions into penetration-testing phases and categorical techniques, it identifies where exploitation occurs, where the flag first appears, and whether the recovered flag is supported by demonstrated behavior. Aggregating solve profiles across agents yields challenge signatures that reveal whether success was achieved via the intended exploit or via shortcut pathways. We apply CTF-ABACUS to 1,435 CTF attempts by six frontier and open-source models on 240 challenges, yielding 2,870 solve profiles under two judge lenses. Trace-verified exploits account for only 62-87% of recovered flags across benchmarks, while shortcut recoveries follow substantially shallower trajectories. These findings shift CTF evaluation from counting recovered flags to verifying demonstrated exploitation and provide a basis for designing benchmarks that better isolate the offensive capabilities.

cs.CR↗

arXiv2026

CTFExplorer: Evaluating LLM Offensive Agents Through Multi-Target Web CTF Benchmarking

Existing benchmarks for LLM-based offensive security agents use isolated, single-target setups with a known vulnerable service and fixed objective. They measure exploitation effectively, but miss how real Capture-the-Flag (CTF) participants triage unknown surfaces, prioritize targets, and allocate effort under uncertainty. Current evaluations therefore fail to assess strategic reasoning beyond exploitation alone. To address this, we introduce \textit{CTFExplorer}, a benchmark suite that shifts offensive security evaluation toward a multi-target setting, which tests how agents explore, prioritize, and chain attacks. CTFExplorer deploys 40 web-based vulnerable services within a single environment, where agents must autonomously discover, distinguish, and exploit targets without predefined guidance. We also present a reactive multi-agent setup as a reference agent framework and develop an agent-agnostic evaluation framework that records structured reasoning traces for fine-grained assessment. This enables behavioral evaluation beyond binary flag capture, such as how agents manage target selection, handle failed hypotheses, coordinate across multiple stages, and extract security intelligence.

cs.CR↗

arXiv2025

Constrained Adversarial Perturbation

Deep neural networks have achieved remarkable success in a wide range of classification tasks. However, they remain highly susceptible to adversarial examples - inputs that are subtly perturbed to induce misclassification while appearing unchanged to humans. Among various attack strategies, Universal Adversarial Perturbations (UAPs) have emerged as a powerful tool for both stress testing model robustness and facilitating scalable adversarial training. Despite their effectiveness, most existing UAP methods neglect domain specific constraints that govern feature relationships. Violating such constraints, such as debt to income ratios in credit scoring or packet flow invariants in network communication, can render adversarial examples implausible or easily detectable, thereby limiting their real world applicability. In this work, we advance universal adversarial attacks to constrained feature spaces by formulating an augmented Lagrangian based min max optimization problem that enforces multiple, potentially complex constraints of varying importance. We propose Constrained Adversarial Perturbation (CAP), an efficient algorithm that solves this problem using a gradient based alternating optimization strategy. We evaluate CAP across diverse domains including finance, IT networks, and cyber physical systems, and demonstrate that it achieves higher attack success rates while significantly reducing runtime compared to existing baselines. Our approach also generalizes seamlessly to individual adversarial perturbations, where we observe similar strong performance gains. Finally, we introduce a principled procedure for learning feature constraints directly from data, enabling broad applicability across domains with structured input spaces.

cs.LG↗

arXiv2025

Cyber security of Mega Events: A Case Study of Securing the Digital Infrastructure for MahaKumbh 2025 -- A 45 days Mega Event of 600 Million Footfalls

Mega events such as the Olympics, World Cup tournaments, G-20 Summit, religious events such as MahaKumbh are increasingly digitalized. From event ticketing, vendor booth or lodging reservations, sanitation, event scheduling, customer service, crime reporting, media streaming and messaging on digital display boards, surveillance, crowd control, traffic control and many other services are based on mobile and web applications, wired and wireless networking, network of Closed-Circuit Television (CCTV) cameras, specialized control room with network and video-feed monitoring. Consequently, cyber threats directed at such digital infrastructure are common. Starting from hobby hackers, hacktivists, cyber crime gangs, to the nation state actors, all target such infrastructure to unleash chaos on an otherwise smooth operation, and often the cyber threat actors attempt to embarrass the organizing country or the organizers. Unlike long-standing organizations such as a corporate or a government department, the infrastructure of mega-events is temporary, constructed over a short time span in expediency, and often shortcuts are taken to make the deadline for the event. As a result, securing such an elaborate yet temporary infrastructure requires a different approach than securing a standard organizational digital infrastructure. In this paper, we describe our approach to securing MahaKumbh 2025, a 600 million footfall event for 45 days in Prayagraj, India, as a cyber security assessment and risk management oversight team. We chronicle the scope, process, methodology, and outcome of our team's effort to secure this mega event. It should be noted that none of the cyber attacks during the 45-day event was successful. Our goal is to put on record the methodology and discuss what we would do differently in case we work on similar future mega event.

cs.CR↗

arXiv2021

Security of Healthcare Data Using Blockchains: A Survey

The advancement in the healthcare sector is entering into a new era in the form of Health 4.0. The integration of innovative technologies like Cyber-Physical Systems (CPS), Big Data, Cloud Computing, Machine Learning, and Blockchain with Healthcare services has led to improved performance and efficiency through data-based learning and interconnection of systems. On the other hand, it has also increased complexities and has brought its own share of vulnerabilities due to the heavy influx, sharing, and storage of healthcare data. The protection of the same from cyber-attacks along with privacy preservation through authenticated access is one of the significant challenges for the healthcare sector. For this purpose, the use of blockchain-based networks can lead to a considerable reduction in the vulnerabilities of the healthcare systems and secure their data. This chapter explores blockchain's role in strengthening healthcare data security by answering the questions related to what data use, when we need, why we need, who needs, and how state-of-the-art techniques use blockchains to secure healthcare data. As a case study, we also explore and analyze the state-of-the-art implementations for blockchain in healthcare data security for the COVID-19 pandemic. In order to provide a path to future research directions, we identify and discuss the technical limitations and regulatory challenges associated with blockchain-based healthcare data security implementation.

cs.CR↗

arXiv2021

Detecting Malicious Accounts in Permissionless Blockchains using Temporal Graph Properties

The temporal nature of modeling accounts as nodes and transactions as directed edges in a directed graph -- for a blockchain, enables us to understand the behavior (malicious or benign) of the accounts. Predictive classification of accounts as malicious or benign could help users of the permissionless blockchain platforms to operate in a secure manner. Motivated by this, we introduce temporal features such as burst and attractiveness on top of several already used graph properties such as the node degree and clustering coefficient. Using identified features, we train various Machine Learning (ML) algorithms and identify the algorithm that performs the best in detecting which accounts are malicious. We then study the behavior of the accounts over different temporal granularities of the dataset before assigning them malicious tags. For Ethereum blockchain, we identify that for the entire dataset - the ExtraTreesClassifier performs the best among supervised ML algorithms. On the other hand, using cosine similarity on top of the results provided by unsupervised ML algorithms such as K-Means on the entire dataset, we were able to detect 554 more suspicious accounts. Further, using behavior change analysis for accounts, we identify 814 unique suspicious accounts across different temporal granularities.

cs.LG↗

arXiv2021

Detecting Malicious Accounts showing Adversarial Behavior in Permissionless Blockchains

Different types of malicious activities have been flagged in multiple permissionless blockchains such as bitcoin, Ethereum etc. While some malicious activities exploit vulnerabilities in the infrastructure of the blockchain, some target its users through social engineering techniques. To address these problems, we aim at automatically flagging blockchain accounts that originate such malicious exploitation of accounts of other participants. To that end, we identify a robust supervised machine learning (ML) algorithm that is resistant to any bias induced by an over representation of certain malicious activity in the available dataset, as well as is robust against adversarial attacks. We find that most of the malicious activities reported thus far, for example, in Ethereum blockchain ecosystem, behaves statistically similar. Further, the previously used ML algorithms for identifying malicious accounts show bias towards a particular malicious activity which is over-represented. In the sequel, we identify that Neural Networks (NN) holds up the best in the face of such bias inducing dataset at the same time being robust against certain adversarial attacks.

cs.CR↗

arXiv2020

Unsupervised Learning Based Robust Multivariate Intrusion Detection System for Cyber-Physical Systems using Low Rank Matrix

Regular and uninterrupted operation of critical infrastructures such as power, transport, communication etc. are essential for proper functioning of a country. Cyber-attacks causing disruption in critical infrastructure service in the past, are considered as a significant threat. With the advancement in technology and the progress of the critical infrastructures towards IP based communication, cyber-physical systems are lucrative targets of the attackers. In this paper, we propose a robust multivariate intrusion detection system called RAD for detecting attacks in the cyber-physical systems in O(d) space and time complexity, where d is the number parameters in the system state vector. The proposed Intrusion Detection System(IDS) is developed in an unsupervised learning setting without using labelled data denoting attacks. It allows a fraction of the training data to be corrupted by outliers or under attack, by subscribing to robust training procedure. The proposed IDS outperforms existing anomaly detection techniques in several real-world datasets and attack scenarios.

cs.CR↗

arXiv2019

Verity: Blockchains to Detect Insider Attacks in DBMS

Integrity and security of the data in database systems are typically maintained with access control policies and firewalls. However, insider attacks -- where someone with an intimate knowledge of the system and administrative privileges tampers with the data -- pose a unique challenge. Measures like append only logging prove to be insufficient because an attacker with administrative privileges can alter logs and login records to eliminate the trace of attack, thus making insider attacks hard to detect. In this paper, we propose Verity -- first of a kind system to the best of our knowledge. Verity serves as a dataless framework by which any blockchain network can be used to store fixed-length metadata about tuples from any SQL database, without complete migration of the database. Verity uses a formalism for parsing SQL queries and query results to check the respective tuples' integrity using blockchains to detect insider attacks. We have implemented our technique using Hyperledger Fabric, Composer REST API, and SQLite database. Using TPC-H data and SQL queries of varying complexity and types, our experiments demonstrate that any overhead of integrity checking remains constant per tuple in a query's results, and scales linearly.

cs.DB↗

arXiv2009

Expressing the Behavior of Three Very Different Concurrent Systems by Using Natural Extensions of Separation Logic

Separation Logic is a non-classical logic used to verify pointer-intensive code. In this paper, however, we show that Separation Logic, along with its natural extensions, can also be used as a specification language for concurrent-system design. To do so, we express the behavior of three very different concurrent systems: a Subway, a Stopwatch, and a 2x2 Switch. The Subway is originally implemented in LUSTRE, the Stopwatch in Esterel, and the 2x2 Switch in Bluespec.

cs.LO↗