14 citations · 43 across the 35 of their papers we have counts for
40 papers
MimicSat: A Reconfigurable Cyber-Physical Testbed For Small Satellite Systems and Cybersecurity Research
Nisha Vinayaga-Sureshkanth, A H M Nazmus Sakib, Mahsin Bin Akram +2
MimicSat provides a common experimental environment for examining how changes in satellite subsystem behavior propagate to mission outcomes across software-based and hardware-based…
Reducing Hallucinated Transcripts in Whisper via Hallucination Space Projection
Maryam Abbasihafshejani, Murtuza Jadliwala
Whisper is a widely used foundation model for automatic speech recognition (ASR), but its generative decoder can produce fluent hallucinated transcripts for inputs containing littl…
Beyond Single-Vulnerability Evaluation: Closing the Engineering Decision Gap Between C Retrofits and Native Safety
Andrew Laramore, Joseph Spracklen, Murtuza Jadliwala
While decades of research have produced numerous retrofitted memory-safety protections for C, these mechanisms are almost exclusively evaluated in isolation, targeting specific vul…
Trust but Verify? Uncovering the Security Debt of Autonomous Coding Agents
A H M Nazmus Sakib, Dipayan Banik, Murtuza Jadliwala
The increasing adoption of autonomous coding agents accelerates software development but also introduces scoped security risks within high-impact file paths that can outpace tradit…
ThermalTap: Passive Application Fingerprinting in VR Headsets via Thermal Side Channels
Mahsin Bin Akram, A H M Nazmus Sakib, OFM Riaz Rahman Aranya +3
Standalone virtual reality (VR) headsets process highly sensitive personal, professional, and health-related data, yet their susceptibility to non-contact physical side channels re…
LLM Ghostbusters: Surgical Package Hallucination Suppression via Adaptive Unlearning
Joseph Spracklen, Pedram Aghazadeh, Farinaz Koushanfar +1
Hallucinations remain an unsolved problem for LLMs, and package hallucinations are a particularly dangerous instance of this phenomenon. Package hallucinations occur during code ge…
Off-The-Shelf Image-to-Image Models Are All You Need To Defeat Image Protection Schemes
Xavier Pleimling, Sifat Muhammad Abdullah, Gunjan Balde +4
Advances in Generative AI (GenAI) have led to the development of various protection strategies to prevent the unauthorized use of images. These methods rely on adding imperceptible…
Prompt and Circumstances: Evaluating the Efficacy of Human Prompt Inference in AI-Generated Art
Khoi Trinh, Scott Seidenberger, Joseph Spracklen +4
The emerging field of AI-generated art has witnessed the rise of prompt marketplaces, where creators can purchase, sell, or share prompts to generate unique artworks. These marketp…
VocalBridge: Latent Diffusion-Bridge Purification for Defeating Perturbation-Based Voiceprint Defenses
Maryam Abbasihafshejani, AHM Nazmus Sakib, Murtuza Jadliwala
The rapid advancement of speech synthesis technologies, including text-to-speech (TTS) and voice conversion (VC), has intensified security and privacy concerns related to voice clo…
Linguistic Hooks: Investigating The Role of Language Triggers in Phishing Emails Targeting African Refugees and Students
Mythili Menon, Nisha Vinayaga-Sureshkanth, Alec Schon +2
Phishing and sophisticated email-based social engineering attacks disproportionately affect vulnerable populations, such as refugees and immigrant students. However, these groups r…
To WASM or Not to WASM: Evaluation of Browser Fingerprinting Defenses Under WASM based Obfuscation
A H M Nazmus Sakib, Mahsin Bin Akram, Joseph Spracklen +4
Browser fingerprinting defenses have historically focused on detecting JavaScript(JS)-based tracking techniques. However, the widespread adoption of WebAssembly (WASM) introduces a…
Optimus: A Robust Defense Framework for Mitigating Toxicity while Fine-Tuning Conversational AI
Aravind Cheruvu, Shravya Kanchi, Sifat Muhammad Abdullah +4
Customizing Large Language Models (LLMs) on untrusted datasets poses severe risks of injecting toxic behaviors. In this work, we introduce Optimus, a novel defense framework design…
A Picture is Worth a Thousand Prompts? Efficacy of Iterative Human-Driven Prompt Refinement in Image Regeneration Tasks
Khoi Trinh, Scott Seidenberger, Raveen Wijewickrama +2
With AI-generated content becoming ubiquitous across the web, social media, and other digital platforms, it is vital to examine how such content are inspired and generated. The cre…
ScooterLab: A Programmable and Participatory Sensing Research Testbed using Micromobility Vehicles
Ubaidullah Khan, Raveen Wijewickrama, Buddhi Ashan M. K. +10
Micromobility vehicles, such as e-scooters, are increasingly popular in urban communities but present significant challenges in terms of road safety, user privacy, infrastructure p…
NinjaDoH: A Censorship-Resistant Moving Target DoH Server Using Hyperscalers and IPNS
Scott Seidenberger, Marc Beret, Raveen Wijewickrama +2
We introduce NinjaDoH, a novel DNS over HTTPS (DoH) protocol that leverages the InterPlanetary Name System (IPNS), along with public cloud infrastructure, to create a censorship-re…
Promptly Yours? A Human Subject Study on Prompt Inference in AI-Generated Art
Khoi Trinh, Joseph Spracklen, Raveen Wijewickrama +3
The emerging field of AI-generated art has witnessed the rise of prompt marketplaces, where creators can purchase, sell, or share prompts for generating unique artworks. These mark…
Unintentional Security Flaws in Code: Automated Defense via Root Cause Analysis
Nafis Tanveer Islam, Mazal Bethany, Dylan Manuel +2
Software security remains a critical concern, particularly as junior developers, often lacking comprehensive knowledge of security practices, contribute to codebases. While there a…
Spiking Neural Networks in Vertical Federated Learning: Performance Trade-offs
Maryam Abbasihafshejani, Anindya Maiti, Murtuza Jadliwala
Federated machine learning enables model training across multiple clients while maintaining data privacy. Vertical Federated Learning (VFL) specifically deals with instances where…
We Have a Package for You! A Comprehensive Analysis of Package Hallucinations by Code Generating LLMs
Joseph Spracklen, Raveen Wijewickrama, A H M Nazmus Sakib +3
The reliance of popular programming languages such as Python and JavaScript on centralized package repositories and open-source software, combined with the emergence of code-genera…
An Analysis of Recent Advances in Deepfake Image Detection in an Evolving Threat Landscape
Sifat Muhammad Abdullah, Aravind Cheruvu, Shravya Kanchi +4
Deepfake or synthetic images produced using deep generative models pose serious risks to online platforms. This has triggered several research efforts to accurately detect deepfake…
Towards a Game-theoretic Understanding of Explanation-based Membership Inference Attacks
Kavita Kumari, Murtuza Jadliwala, Sumit Kumar Jha +1
Model explanations improve the transparency of black-box machine learning (ML) models and their decisions; however, they can also be exploited to carry out privacy threats such as…
Causative Insights into Open Source Software Security using Large Language Code Embeddings and Semantic Vulnerability Graph
Nafis Tanveer Islam, Gonzalo De La Torre Parra, Dylan Manual +2
Open Source Software (OSS) security and resilience are worldwide phenomena hampering economic and technological innovation. OSS vulnerabilities can cause unauthorized access, data…
OverHear: Headphone based Multi-sensor Keystroke Inference
Raveen Wijewickrama, Maryam Abbasihafshejani, Anindya Maiti +1
Headphones, traditionally limited to audio playback, have evolved to integrate sensors like high-definition microphones and accelerometers. While these advancements enhance user ex…
TorMult: Introducing a Novel Tor Bandwidth Inflation Attack
Christoph Sendner, Jasper Stang, Alexandra Dmitrienko +2
The Tor network is the most prominent system for providing anonymous communication to web users, with a daily user base of 2 million users. However, since its inception, it has bee…