Surya Nepal
YOU?
Author Swipe
View article: Keep the Lights On, Keep the Lengths in Check: Plug-In Adversarial Detection for Time-Series LLMs in Energy Forecasting
Keep the Lights On, Keep the Lengths in Check: Plug-In Adversarial Detection for Time-Series LLMs in Energy Forecasting Open
Accurate time-series forecasting is increasingly critical for planning and operations in low-carbon power systems. Emerging time-series large language models (TS-LLMs) now deliver this capability at scale, requiring no task-specific retrai…
View article: Community-Based Risk Analysis: Assessing Multi-Hazard Vulnerabilities in Urban Kampungs in Surabaya, Indonesia
Community-Based Risk Analysis: Assessing Multi-Hazard Vulnerabilities in Urban Kampungs in Surabaya, Indonesia Open
Urban kampungs in Surabaya, Indonesia, face layered vulnerabilities due to overlapping envi-ronmental hazards, socioeconomic precarity, and limited infrastructural support. Despite being central to the city’s cultural and spatial fabric, t…
View article: RINSER: Accurate API Prediction Using Masked Language Models
RINSER: Accurate API Prediction Using Masked Language Models Open
Malware authors commonly use obfuscation to hide API identities in binary files, making analysis difficult and time-consuming for a human expert to understand the behavior and intent of the program. Automatic API prediction tools are neces…
View article: OblivCDN: A Practical Privacy-preserving CDN with Oblivious Content Access
OblivCDN: A Practical Privacy-preserving CDN with Oblivious Content Access Open
Content providers increasingly utilise Content Delivery Networks (CDNs) to enhance users' content download experience. However, this deployment scenario raises significant security concerns regarding content confidentiality and user privac…
View article: Smart Pin Security in ATM Transaction on Graphical Password Interchange
Smart Pin Security in ATM Transaction on Graphical Password Interchange Open
The vital issue in data security is client confirmation. There are numerous confirmation strategies are printed, graphical or biometric passwords etc. The content based watchword is effectively speculated by the assailant over to adjacent …
View article: What is the Cost of Differential Privacy for Deep Learning-Based Trajectory Generation?
What is the Cost of Differential Privacy for Deep Learning-Based Trajectory Generation? Open
While location trajectories offer valuable insights, they also reveal sensitive personal information. Differential Privacy (DP) offers formal protection, but achieving a favourable utility-privacy trade-off remains challenging. Recent work…
View article: ContextBuddy: AI-Enhanced Contextual Insights for Security Alert Investigation (Applied to Intrusion Detection)
ContextBuddy: AI-Enhanced Contextual Insights for Security Alert Investigation (Applied to Intrusion Detection) Open
Modern Security Operations Centres (SOCs) integrate diverse tools, such as SIEM, IDS, and XDR systems, offering rich contextual data, including alert enrichments, flow features, and similar case histories. Yet, analysts must still manually…
View article: Bridging Expertise Gaps: The Role of LLMs in Human-AI Collaboration for Cybersecurity
Bridging Expertise Gaps: The Role of LLMs in Human-AI Collaboration for Cybersecurity Open
This study investigates whether large language models (LLMs) can function as intelligent collaborators to bridge expertise gaps in cybersecurity decision-making. We examine two representative tasks-phishing email detection and intrusion de…
View article: Saving Storage Space Using Files on the Web
Saving Storage Space Using Files on the Web Open
As conventional storage density reaches its physical limits, the cost of a gigabyte of storage is no longer plummeting, but rather has remained mostly flat for the past decade. Meanwhile, file sizes continue to grow, leading to ever fuller…
View article: Alert Fatigue in Security Operations Centres: Research Challenges and Opportunities
Alert Fatigue in Security Operations Centres: Research Challenges and Opportunities Open
A security operations centre (SOC) is a facility where teams of security professionals, supported by advanced technologies and processes, work together to monitor, detect, and respond to cybersecurity incidents. With advances in AI technol…
View article: Provisioning Time-Based Subscription in NDN: A Secure and Efficient Access Control Scheme
Provisioning Time-Based Subscription in NDN: A Secure and Efficient Access Control Scheme Open
This paper proposes a novel encryption-based access control mechanism for Named Data Networking (NDN). The scheme allows data producers to share their content in encrypted form before transmitting it to consumers. The encryption mechanism …
View article: Comprehensive Evaluation of Cloaking Backdoor Attacks on Object Detector in Real-World
Comprehensive Evaluation of Cloaking Backdoor Attacks on Object Detector in Real-World Open
The exploration of backdoor vulnerabilities in object detectors, particularly in real-world scenarios, remains limited. A significant challenge lies in the absence of a natural physical backdoor dataset, and constructing such a dataset is …
View article: Bridging Expertise Gaps: The Role of LLMs in Human-AI Collaboration for Cybersecurity
Bridging Expertise Gaps: The Role of LLMs in Human-AI Collaboration for Cybersecurity Open
View article: Adversarial Attacks Against Automated Fact-Checking: A Survey
Adversarial Attacks Against Automated Fact-Checking: A Survey Open
View article: Watch Out! Simple Horizontal Class Backdoor Can Trivially Evade Defense
Watch Out! Simple Horizontal Class Backdoor Can Trivially Evade Defense Open
View article: SoK: The Security-Safety Continuum of Multimodal Foundation Models through Information Flow and Global Game-Theoretic Analysis of Asymmetric Threats
SoK: The Security-Safety Continuum of Multimodal Foundation Models through Information Flow and Global Game-Theoretic Analysis of Asymmetric Threats Open
Multimodal foundation models (MFMs) integrate diverse data modalities to support complex and wide-ranging tasks. However, this integration also introduces distinct safety and security challenges. In this paper, we unify the concepts of saf…
View article: Analyzing One- and Two-bit Data to Reduce Memory Requirements for <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"> <mml:mi>F</mml:mi> </mml:math> -statistic-based Gravitational Wave Searches
Analyzing One- and Two-bit Data to Reduce Memory Requirements for -statistic-based Gravitational Wave Searches Open
Searches for continuous-wave gravitational radiation in data collected by modern long-baseline interferometers, such as the Laser Interferometer Gravitational-wave Observatory (LIGO), the Virgo interferometer, and the Kamioka Gravitational…
View article: From Solitary Directives to Interactive Encouragement! LLM Secure Code Generation by Natural Language Prompting
From Solitary Directives to Interactive Encouragement! LLM Secure Code Generation by Natural Language Prompting Open
Large Language Models (LLMs) have shown remarkable potential in code generation, making them increasingly important in the field. However, the security issues of generated code have not been fully addressed, and the usability of LLMs in co…
View article: Adversarially Guided Stateful Defense Against Backdoor Attacks in Federated Deep Learning
Adversarially Guided Stateful Defense Against Backdoor Attacks in Federated Deep Learning Open
Recent works have shown that Federated Learning (FL) is vulnerable to backdoor attacks. Existing defenses cluster submitted updates from clients and select the best cluster for aggregation. However, they often rely on unrealistic assumptio…
View article: Alert Prioritisation in Security Operations Centres: A Systematic Survey on Criteria and Methods
Alert Prioritisation in Security Operations Centres: A Systematic Survey on Criteria and Methods Open
Security Operations Centres (SOCs) are specialised facilities where security analysts leverage advanced technologies to monitor, detect and respond to cyber incidents. However, the increasing volume of security incidents has overwhelmed se…
View article: SAFE: Advancing Large Language Models in Leveraging Semantic and Syntactic Relationships for Software Vulnerability Detection
SAFE: Advancing Large Language Models in Leveraging Semantic and Syntactic Relationships for Software Vulnerability Detection Open
Software vulnerabilities (SVs) have emerged as a prevalent and critical concern for safety-critical security systems. This has spurred significant advancements in utilizing AI-based methods, including machine learning and deep learning, fo…
View article: Honeyfile Camouflage: Hiding Fake Files in Plain Sight
Honeyfile Camouflage: Hiding Fake Files in Plain Sight Open
Honeyfiles are a particularly useful type of honeypot: fake files deployed to detect and infer information from malicious behaviour. This paper considers the challenge of naming honeyfiles so they are camouflaged when placed amongst real f…
View article: SoK: Can Trajectory Generation Combine Privacy and Utility?
SoK: Can Trajectory Generation Combine Privacy and Utility? Open
While location trajectories represent a valuable data source for analyses and location-based services, they can reveal sensitive information, such as political and religious preferences. Differentially private publication mechanisms have b…
View article: Systematic Literature Review of AI-enabled Spectrum Management in 6G and Future Networks
Systematic Literature Review of AI-enabled Spectrum Management in 6G and Future Networks Open
Artificial Intelligence (AI) has advanced significantly in various domains like healthcare, finance, and cybersecurity, with successes such as DeepMind's medical imaging and Tesla's autonomous vehicles. As telecommunications transition fro…
View article: Towards Human-AI Teaming to Mitigate Alert Fatigue in Security Operations Centres
Towards Human-AI Teaming to Mitigate Alert Fatigue in Security Operations Centres Open
Security Operations Centres (SOCs) play a pivotal role in defending organisations against evolving cyber threats. They function as central hubs for detecting, analysing, and responding promptly to cyber incidents with the primary objective…
View article: Leakage-Resilient and Carbon-Neutral Aggregation Featuring the Federated AI-enabled Critical Infrastructure
Leakage-Resilient and Carbon-Neutral Aggregation Featuring the Federated AI-enabled Critical Infrastructure Open
AI-enabled critical infrastructures (ACIs) integrate artificial intelligence (AI) technologies into various essential systems and services that are vital to the functioning of society, offering significant implications for efficiency, secu…
View article: Annotated Check List of Ichthyofaunal Diversity in the Freshwater Tidal Stretch Along the Gosthani Estuary, Bheemunipatnam, East Coast of India
Annotated Check List of Ichthyofaunal Diversity in the Freshwater Tidal Stretch Along the Gosthani Estuary, Bheemunipatnam, East Coast of India Open
The present study found 60 fish species belonging to 20 orders, 38 families, and 54 genera in the Gosthani estuary between May 2023 and April 2024. The fishes were brought to the lab and placed in glass jars before being preserved in a 9-1…
View article: Privacy-Preserving and Fairness-Aware Federated Learning for Critical Infrastructure Protection and Resilience
Privacy-Preserving and Fairness-Aware Federated Learning for Critical Infrastructure Protection and Resilience Open
The energy industry is undergoing significant transformations as it strives to achieve net-zero emissions and future-proof its infrastructure, where every participant in the power grid has the potential to both consume and produce energy r…
View article: Hyperlink Hijacking: Exploiting Erroneous URL Links to Phantom Domains
Hyperlink Hijacking: Exploiting Erroneous URL Links to Phantom Domains Open
Web users often follow hyperlinks hastily, expecting them to be correctly programmed.However, it is possible those links contain typos or other mistakes.By discovering active but erroneous hyperlinks, a malicious actor can spoof a website …
View article: Deep Learning-Based Out-of-distribution Source Code Data Identification: How Far Have We Gone?
Deep Learning-Based Out-of-distribution Source Code Data Identification: How Far Have We Gone? Open
Software vulnerabilities (SVs) have become a common, serious, and crucial concern to safety-critical security systems. That leads to significant progress in the use of AI-based methods for software vulnerability detection (SVD). In practic…