arXiv subjects

Ankit Gangwal

Publications and source records attributed to Ankit Gangwal.

15 recordsLinked to original sources

arXiv2026

PatchPoison: Poisoning Multi-View Datasets to Degrade 3D Reconstruction

3D Gaussian Splatting (3DGS) has recently enabled highly photorealistic 3D reconstruction from casually captured multi-view images. However, this accessibility raises a privacy concern: publicly available images or videos can be exploited to reconstruct detailed 3D models of scenes or objects without the owner's consent. We present PatchPoison, a lightweight dataset-poisoning method that prevents unauthorized 3D reconstruction. Unlike global perturbations, PatchPoison injects a small high-frequency adversarial patch, a structured checkerboard, into the periphery of each image in a multi-view dataset. The patch is designed to corrupt the feature-matching stage of Structure-from-Motion (SfM) pipelines such as COLMAP by introducing spurious correspondences that systematically misalign estimated camera poses. Consequently, downstream 3DGS optimization diverges from the correct scene geometry. On the NeRF-Synthetic benchmark, inserting a 12 X 12 pixel patch increases reconstruction error by 6.8x in LPIPS, while the poisoned images remain unobtrusive to human viewers. PatchPoison requires no pipeline modifications, offering a practical, "drop-in" preprocessing step for content creators to protect their multi-view data.

cs.CV↗

arXiv2025

LoReTTA: A Low Resource Framework To Poison Continuous Time Dynamic Graphs

Temporal Graph Neural Networks (TGNNs) are increasingly used in high-stakes domains, such as financial forecasting, recommendation systems, and fraud detection. However, their susceptibility to poisoning attacks poses a critical security risk. We introduce LoReTTA (Low Resource Two-phase Temporal Attack), a novel adversarial framework on Continuous-Time Dynamic Graphs, which degrades TGNN performance by an average of 29.47% across 4 widely benchmark datasets and 4 State-of-the-Art (SotA) models. LoReTTA operates through a two-stage approach: (1) sparsify the graph by removing high-impact edges using any of the 16 tested temporal importance metrics, (2) strategically replace removed edges with adversarial negatives via LoReTTA's novel degree-preserving negative sampling algorithm. Our plug-and-play design eliminates the need for expensive surrogate models while adhering to realistic unnoticeability constraints. LoReTTA degrades performance by upto 42.0% on MOOC, 31.5% on Wikipedia, 28.8% on UCI, and 15.6% on Enron. LoReTTA outperforms 11 attack baselines, remains undetectable to 4 leading anomaly detection systems, and is robust to 4 SotA adversarial defense training methods, establishing its effectiveness, unnoticeability, and robustness.

cs.LG↗

arXiv2025

Merge Now, Regret Later: The Hidden Cost of Model Merging Is Adversarial Transferability

Model Merging (MM) has proven to be an effective alternative to multi-task learning, where several fine-tuned models are merged, without access to the tasks' training data, into one model that retains performance across different tasks. Recent works have explored the security of MM, showing how MM can confer robustness against various adversarial attacks. However, none of them has sufficiently explored its impact on transfer attacks using transferable adversarial examples. In this work, we study the effect of MM on the transferability of adversarial examples. We perform comprehensive evaluations and statistical analysis consisting of eight MM methods, seven datasets, and six attack methods, sweeping over 336 distinct attack settings. Through it, we first challenge the prevailing notion of MM conferring free adversarial robustness, and show that MM cannot reliably defend against transfer attacks, with over 80% transfer rate. Moreover, we reveal two key insights for machine-learning practitioners regarding MM and transferability for a robust system design: (1) stronger MM methods increase vulnerability to transfer attacks and (2) mitigating representation bias increases vulnerability to transfer attacks. We also find weight averaging as an exception to (1), i.e., it is found to be the most vulnerable method to transfer attacks, despite being the weakest MM method. Finally, we analyze the underlying reasons for these findings, show how an adversary with limited information could launch an attack, and provide potential solutions. These findings offer actionable insights for deploying MM in security-sensitive machine-learning systems.

cs.LG↗

arXiv2025

KeTS: Kernel-based Trust Segmentation against Model Poisoning Attacks

Federated Learning (FL) enables multiple users to collaboratively train a global model in a distributed manner without revealing their personal data. However, FL remains vulnerable to model poisoning attacks, where malicious actors inject crafted updates to compromise the global model's accuracy. We propose a novel defense mechanism, Kernel-based Trust Segmentation (KeTS), to counter model poisoning attacks. Unlike existing approaches, KeTS analyzes the evolution of each client's updates and effectively segments malicious clients using Kernel Density Estimation (KDE), even in the presence of benign outliers. We thoroughly evaluate KeTS's performance against the six most effective model poisoning attacks (i.e., Trim-Attack, Krum-Attack, Min-Max attack, Min-Sum attack, and their variants) on four different datasets (i.e., MNIST, Fashion-MNIST, CIFAR-10, and KDD-CUP-1999) and compare its performance with three classical robust schemes (i.e., Krum, Trim-Mean, and Median) and a state-of-the-art defense (i.e., FLTrust). Our results show that KeTS outperforms the existing defenses in every attack setting; beating the best-performing defense by an overall average of >24% (on MNIST), >14% (on Fashion-MNIST), >9% (on CIFAR-10), >11% (on KDD-CUP-1999). A series of further experiments (varying poisoning approaches, attacker population, etc.) reveal the consistent and superior performance of KeTS under diverse conditions. KeTS is a practical solution as it satisfies all three defense objectives (i.e., fidelity, robustness, and efficiency) without imposing additional overhead on the clients. Finally, we also discuss a simple, yet effective extension to KeTS to handle consistent-untargeted (e.g., sign-flipping) attacks as well as targeted attacks (e.g., label-flipping).

cs.CR↗

arXiv2024

CSUM: A Novel Mechanism for Updating CubeSat while Preserving Authenticity and Integrity

The recent rise of CubeSat has revolutionized global space explorations, as it offers cost-effective solutions for low-orbit space applications (including climate monitoring, weather measurements, communications, and earth observation). A salient feature of CubeSat is that applications currently on-boarded can either be updated or entirely replaced by new applications via software updates, which allows reusing in-orbit hardware, reduces space debris, and saves cost as well as time. Securing software updates employing traditional methods (e.g., encryption) remains impractical mainly due to the low-resource capabilities of CubeSat. Therefore, the security of software updates for CubeSats remains a critical issue. In this paper, we propose CubeSat Update Mechanism (CSUM), a lightweight scheme to provide integrity, authentication, and data freshness guarantees for software update broadcasts to CubeSats using a hash chain. We empirically evaluate our proof of concept implementation to demonstrate the feasibility and effectiveness of our approach. CSUM can validate 50,000 consecutive updates successfully in less than a second. We also perform a comparative analysis of different cryptographic primitives. Our empirical evaluations show that the hash-based approach is at least 61$\times$ faster than the conventional mechanisms, even in resource-constrained environments. Finally, we discuss the limitations, challenges, and potential future research directions for CubeSat software update procedures.

cs.CR↗

arXiv2024

GENIE: Watermarking Graph Neural Networks for Link Prediction

The rapid adoption, usefulness, and resource-intensive training of Graph Neural Network (GNN) models have made them an invaluable intellectual property in graph-based machine learning. However, their wide-spread adoption also makes them susceptible to stealing, necessitating robust Ownership Demonstration (OD) techniques. Watermarking is a promising OD framework for deep neural networks, but existing methods fail to generalize to GNNs due to the non-Euclidean nature of graph data. Existing works on GNN watermarking primarily focus on node and graph classification, overlooking Link Prediction (LP). In this paper, we propose GENIE (watermarking Graph nEural Networks for lInk prEdiction), the first scheme to watermark GNNs for LP. GENIE creates a novel backdoor for both node-representation and subgraph-based LP methods, utilizing a unique trigger set and a secret watermark vector. Our OD scheme is equipped with Dynamic Watermark Thresholding (DWT), ensuring high verification probability while addressing practical issues in existing OD schemes. We extensively evaluate GENIE across 4 diverse model architectures (i.e., SEAL, GCN, GraphSAGE and NeoGNN), 7 real-world datasets and 21 watermark removal techniques and demonstrate its robustness to watermark removal and ownership piracy attacks. Finally, we discuss adaptive attacks against GENIE and a defense strategy to counter it. The codebase and related artifacts are publicly available at our Project Page.

cs.CR↗

arXiv2023

De-authentication using Ambient Light Sensor

While user authentication happens before initiating or resuming a login session, de-authentication detects the absence of a previously-authenticated user to revoke her currently active login session. The absence of proper de-authentication can lead to well-known lunchtime attacks, where a nearby adversary takes over a carelessly departed user's running login session. The existing solutions for automatic de-authentication have distinct practical limitations, e.g., extraordinary deployment requirements or high initial cost of external equipment. In this paper, we propose "DE-authentication using Ambient Light sensor" (DEAL), a novel, inexpensive, fast, and user-friendly de-authentication approach. DEAL utilizes the built-in ambient light sensor of a modern computer to determine if the user is leaving her work-desk. DEAL, by design, is resilient to natural shifts in lighting conditions and can be configured to handle abrupt changes in ambient illumination (e.g., due to toggling of room lights). We collected data samples from 4800 sessions with 120 volunteers in 4 typical workplace settings and conducted a series of experiments to evaluate the quality of our proposed approach thoroughly. Our results show that DEAL can de-authenticate a departing user within 4 seconds with a hit rate of 89.15% and a fall-out of 7.35%. Finally, bypassing DEAL to launch a lunchtime attack is practically infeasible as it requires the attacker to either take the user's position within a few seconds or manipulate the sensor readings sophisticatedly in real-time.

cs.CR↗

arXiv2022

On the Feasibility of Profiling Electric Vehicles through Charging Data

Electric vehicles (EVs) represent the long-term green substitute for traditional fuel-based vehicles. To encourage EV adoption, the trust of the end-users must be assured. In this work, we focus on a recently emerging privacy threat of profiling and identifying EVs via the analog electrical data exchanged during the EV charging process. The core focus of our work is to investigate the feasibility of such a threat at scale. To this end, we first propose an improved EV profiling approach that outperforms the state-of-the-art EV profiling techniques. Next, we exhaustively evaluate the performance of our improved approach to profile EVs in real-world settings. In our evaluations, we conduct a series of experiments including 25032 charging sessions from 530 real EVs, sub-sampled datasets with different data distributions, etc. Our results show that even with our improved approach, profiling and individually identifying the growing number of EVs is not viable in practice; at least with the analog charging data utilized throughout the literature. We believe that our findings from this work will further foster the trust of potential users in the EV ecosystem, and consequently, encourage EV adoption.

cs.CR↗

arXiv2022

A Survey of Layer-Two Blockchain Protocols

After the success of the Bitcoin blockchain, came several cryptocurrencies and blockchain solutions in the last decade. Nonetheless, Blockchain-based systems still suffer from low transaction rates and high transaction processing latencies, which hinder blockchains' scalability. An entire class of solutions, called Layer-1 scalability solutions, have attempted to incrementally improve such limitations by adding/modifying fundamental blockchain attributes. Recently, a completely different class of works, called Layer-2 protocols, have emerged to tackle the blockchain scalability issues using unconventional approaches. Layer-2 protocols improve transaction processing rates, periods, and fees by minimizing the use of underlying slow and costly blockchains. In fact, the main chain acts just as an instrument for trust establishment and dispute resolution among Layer-2 participants, where only a few transactions are dispatched to the main chain. Thus, Layer-2 blockchain protocols have the potential to transform the domain. However, rapid and discrete developments have resulted in diverse branches of Layer-2 protocols. In this work, we systematically create a broad taxonomy of such protocols and implementations. We discuss each Layer-2 protocol class in detail and also elucidate their respective approaches, salient features, requirements, etc. Moreover, we outline the issues related to these protocols along with a comparative discussion. Our thorough study will help further systematize the knowledge dispersed in the domain and help the readers to better understand the field of Layer-2 protocols.

cs.CR↗

arXiv2022

BLEWhisperer: Exploiting BLE Advertisements for Data Exfiltration

Bluetooth technology has enabled short-range wireless communication for billions of devices. Bluetooth Low-Energy (BLE) variant aims at improving power consumption on battery-constrained devices. BLE-enabled devices broadcast information (e.g., as beacons) to nearby devices via advertisements. Unfortunately, such functionality can become a double-edged sword at the hands of attackers. In this paper, we primarily show how an attacker can exploit BLE advertisements to exfiltrate information from BLE-enable devices. In particular, our attack establishes a communication medium between two devices without requiring any prior authentication or pairing. We develop a proof-of-concept attack framework on the Android ecosystem and assess its performance via a thorough set of experiments. Our results indicate that such an exfiltration attack is indeed possible though with a limited data rate. Nevertheless, we also demonstrate potential use cases and enhancements to our attack that can further its severeness. Finally, we discuss possible countermeasures to prevent such an attack.

cs.CR↗

arXiv2020

Detecting Covert Cryptomining using HPC

Cybercriminals have been exploiting cryptocurrencies to commit various unique financial frauds. Covert cryptomining - which is defined as an unauthorized harnessing of victims' computational resources to mine cryptocurrencies - is one of the prevalent ways nowadays used by cybercriminals to earn financial benefits. Such exploitation of resources causes financial losses to the victims. In this paper, we present our novel and efficient approach to detect covert cryptomining. Our solution is a generic solution that, unlike currently available solutions to detect covert cryptomining, is not tailored to a specific cryptocurrency or a particular form of cryptomining. In particular, we focus on the core mining algorithms and utilize Hardware Performance Counters (HPC) to create clean signatures that grasp the execution pattern of these algorithms on a processor. We built a complete implementation of our solution employing advanced machine learning techniques. We evaluated our methodology on two different processors through an exhaustive set of experiments. In our experiments, we considered all the cryptocurrencies mined by the top-10 mining pools, which collectively represent the largest share (84% during Q3 2018) of the cryptomining market. Our results show that our classifier can achieve a near-perfect classification with samples of length as low as five seconds. Due to its robust and practical design, our solution can even adapt to zero-day cryptocurrencies. Finally, we believe our solution is scalable and can be deployed to tackle the uprising problem of covert cryptomining.

cs.CR↗

arXiv2020

Improving Password Guessing via Representation Learning

Learning useful representations from unstructured data is one of the core challenges, as well as a driving force, of modern data-driven approaches. Deep learning has demonstrated the broad advantages of learning and harnessing such representations. In this paper, we introduce a deep generative model representation learning approach for password guessing. We show that an abstract password representation naturally offers compelling and versatile properties that can be used to open new directions in the extensively studied, and yet presently active, password guessing field. These properties can establish novel password generation techniques that are neither feasible nor practical with the existing probabilistic and non-probabilistic approaches. Based on these properties, we introduce:(1) A general framework for conditional password guessing that can generate passwords with arbitrary biases; and (2) an Expectation Maximization-inspired framework that can dynamically adapt the estimated password distribution to match the distribution of the attacked password set.

cs.CR↗

arXiv2019

The Road Ahead for Networking: A Survey on ICN-IP Coexistence Solutions

In recent years, the current Internet has experienced an unexpected paradigm shift in the usage model, which has pushed researchers towards the design of the Information-Centric Networking (ICN) paradigm as a possible replacement of the existing architecture. Even though both Academia and Industry have investigated the feasibility and effectiveness of ICN, achieving the complete replacement of the Internet Protocol (IP) is a challenging task. Some research groups have already addressed the coexistence by designing their own architectures, but none of those is the final solution to move towards the future Internet considering the unaltered state of the networking. To design such architecture, the research community needs now a comprehensive overview of the existing solutions that have so far addressed the coexistence. The purpose of this paper is to reach this goal by providing the first comprehensive survey and classification of the coexistence architectures according to their features (i.e., deployment approach, deployment scenarios, addressed coexistence requirements and architecture or technology used) and evaluation parameters (i.e., challenges emerging during the deployment and the runtime behaviour of an architecture). We believe that this paper will finally fill the gap required for moving towards the design of the final coexistence architecture.

cs.NI↗

arXiv2019

Blockchain Trilemma Solver Algorand has Dilemma over Undecidable Messages

Recently, an ingenious protocol called Algorand has been proposed to overcome these limitations. Algorand uses an innovative process - called cryptographic sortition - to securely and unpredictably elect a set of voters from the network periodically. These voters are responsible for reaching consensus through a Byzantine Agreement (BA) protocol on one block per time, guaranteeing an overwhelming probability of linearity of the blockchain. In this paper, we present a security analysis of Algorand. To the best of our knowledge, it is the first security analysis as well as the first formal study on Algorand. We designed an attack scenario in which a group of malicious users tries to break the protocol, or at least limiting it to a reduced partition of network users, by exploiting a possible security flaw in the messages validation process of the BA. Since the source code or an official simulator for Algorand was not available at the time of our study, we created a simulator (which is available on request) to implement the protocol and assess the feasibility of our attack scenario. Our attack requires the attacker to have a trivial capability of establishing multiple connections with targeted nodes and costs practically nothing to the attacker. Our results show that it is possible to slow down the message validation process on honest nodes, which eventually forces them to choose default values on the consensus; leaving the targeted nodes behind in the chain as compared to the non-attacked nodes. Even though our results are subject to the real implementation assumption, the core concept of our attack remains valid.

cs.CR↗

arXiv2018

On the Economic Significance of Ransomware Campaigns: A Bitcoin Transactions Perspective

Bitcoin cryptocurrency system enables users to transact securely and pseudo-anonymously by using an arbitrary number of aliases (Bitcoin addresses). Cybercriminals exploit these characteristics to commit immutable and presumably untraceable monetary fraud, especially via ransomware; a type of malware that encrypts files of the infected system and demands ransom for decryption. In this paper, we present our comprehensive study on all recent ransomware and report the economic impact of such ransomware from the Bitcoin payment perspective. We also present a lightweight framework to identify, collect, and analyze Bitcoin addresses managed by the same user or group of users (cybercriminals, in this case), which includes a novel approach for classifying a payment as ransom. To verify the correctness of our framework, we compared our findings on CryptoLocker ransomware with the results presented in the literature. Our results align with the results found in the previous works except for the final valuation in USD. The reason for this discrepancy is that we used the average Bitcoin price on the day of each ransom payment whereas the authors of the previous studies used the Bitcoin price on the day of their evaluation. Furthermore, for each investigated ransomware, we provide a holistic view of its genesis, development, the process of infection and execution, and characteristic of ransom demands. Finally, we also release our dataset that contains a detailed transaction history of all the Bitcoin addresses we identified for each ransomware.

cs.CR↗