Abstract

In this paper, we present a deterministic -round algorithm for the 2-ruling set problem in the sublinear Massively Parallel Computation (MPC) model. This improves upon the fastest known deterministic 2-ruling set algorithm for this model, which is the -round algorithm by Giliberti and Parsaeian (PODC 2024). Our result is obtained by derandomizing the “sample-and-gather” approach of Kothapalli, Pai, and Pemmaraju (FSTTCS 2020). The “sample-and-gather” approach involves making random sampling decisions, not just for the current iteration, but a batch of future iterations. Thus, derandomizing this approach requires the “fixing” of randomness for a batch of future iterations. We further extend our results to show that a β -ruling set for β ≥ 2 can be obtained in deterministic rounds in the sublinear MPC model. Additionally, we present a deterministic β -ruling set algorithms for sparse graphs (i.e., bounded arboricity graphs) where β ≥ 2, which runs in rounds for arboricity-λ graphs in the sublinear MPC model

Abstract

Reconfiguring two shortest paths in a graph means modifying one shortest path to the other by changing one vertex at a time so that all the intermediate paths are also shortest paths. This problem has several natural applications, namely: (a) repaving road networks, (b) rerouting data packets in a synchronous multiprocessing setting, (c) the shipping container stowage problem, and (d) the train marshalling problem. When modelled as graph problems, (a) is the most general case while (b), (c), (d) are restrictions to different graph classes. We show that (a) does not admit polynomial-time algorithms (assuming ), even for relaxed variants of the problem (assuming ). For (b), (c), (d), we present polynomial-time algorithms to solve the respective problems. We also generalize the problem to when at most k (for a fixed integer ) contiguous vertices on a shortest path can be changed at a time.

Abstract

Image Attribution seeks to reveal the importance of image regions in the classifier’s final decision. Of the various ways to tackle this problem, the optimization based perspective is particularly intuitive: It applies the attribution as a mask on the image and reduces the attribution task to a loss, that can be optimized using gradient descent. Previous work has considered the goal as searching for the single best mask. Under this setup, however, there is a tendency towards trivial solutions of large masks with reduced discernment of the relative importances of regions. This has typically required auxiliary loss terms to control the area of the mask, however, their strength relative to the primary loss needs to be tuned. We challenge this necessity, by re-imagining attribution as an ordering of pixels according to importance. This ordering may be interpreted as a schedule which determines which locations get seen earlier and which later, allowing us to create a trajectory of masks from completely OFF to completely ON. We optimize through this sequence of masks of “all” areas and not just a single mask as in previous methods. We explore this setting, which we dub Saliency-as-Schedule (SaS), and demonstrate its effectiveness through experiments in a variety of settings, involving multiple datasets and CNN architectures. Further, we also propose a novel attribution task, feature saliency, where we use SaS to rate the influence of image regions on the intermediate feature maps of a CNN, and not just the class logit. Our findings suggest that SaS is a promising direction for the attribution problem. Our code will be available at https://github.com/tumbleweed/SaliencyasSchedule

Abstract

Image Attribution is the task of ascribing importance to regions of the input, for the final decision of a classifier. Many methods for attribution exist, and a recent development has been to use the image at multiple scales to improve the performance of some lightweight attribution methods. These gains have been demonstrated for methods that require a single or multiple but independent forward passes through the network; however, they haven’t been explored in the context of optimization-based attribution (OA) methods. As compared to other techniques, like CAMs or axiomatic methods, OA is attractive as it lends a natural formulation of the task without the need for any heuristic rules. However, the iterative way of solving the optimization problem presents challenges to straightforward utilization of multiple scales. We investigate this scenario and develop a novel 2-step approach that first discovers promising areas across scales and locations from the input and then runs Optimization based Attribution on them. We find that while a naive incorporation of image crops is unsuccessful, this 2-stage pipeline leads to improvements in performance. We provide qualitative and quantitative evidence for this and investigate the reasons for the improvement via multiple ablation experiments.

Abstract

In the present era, the increasing number of network devices and ubiquitous computing leads to the flow of enormous amounts of data traffic, including sensitive and confidential information, on the internet and carrying out commercial and banking transactions online. This gives cybercriminals an opportunity to launch an attack like phishing to steal confidential information from the user and gain unauthorized access. This can be mitigated by the help of an intelligent machine learningbased phishing detection system, which can detect potential phishing attacks and take appropriate action. In this paper, we have addressed this major cyber issue and proposed a machine learning-based phishing detection scheme (in short, EM-PAD), which is trained on a benchmark dataset and evaluated on standard metrics: F1-score and Accuracy. The proposed model is compared with different existing schemes based on Accuracy, indicating that it has outperformed them with remarkable results

Abstract

In the realm of smart city surveillance, consumer electronics (CE) devices communicate through vulnerable wireless channels, posing significant security risks. To ensure secure and uninterrupted services for residents, continuous monitoring is imperative. Existing authentication methods for CE in smart cities authenticate users/devices at the onset of a communication session, assuming they remain authenticated throughout. However, temporary access by an attacker to the user's or CE device can lead to impersonation. To mitigate this security threat, we propose a continuous authentication (CA) protocol utilizing vector similarity search (VSS), which has emerged as a novel approach to enhance security and privacy in CE deployed within smart city surveillance systems. Through the employment of VSS techniques and secure communication via session key establishment, the proposed scheme continuously monitors user behavior and verifies legitimacy, ensuring seamless operation and protection against a myriad of potential threats. This innovative framework enhances the resilience of smart city infrastructures against unauthorized access, data tampering, data poisoning attacks, and other malicious activities.

Abstract

In facial recognition systems, quality extends beyond conventional perceptual quality to features incorporating identity information. Most facial image datasets embark on factors such as illumination and pose, making current systems robust enough to these factors with impressive recognition performance. Still, it is imperative to acknowledge that age variation and emotional similarity significantly influence identity. Variations in these features might significantly deceive the FR systems. These features also serve as easy channels for adversarial attacks on FR systems that alter facial features, such as morphing. Hence, making FR systems sensitive to the variations introduced over the range of these features is critical. We propose that the Unified Tri-Feature Quality Metric (U3FQ) be incorporated. This novel assessment framework integrates three critical elements: age variance, facial expression similarity, and congruence scores from state-of-the-art recognition models such as VGG-Face, ArcFace, FaceNet, and OpenFace. The weighting U3FQ utilizes an advanced learning paradigm, employing a Regression Network model for facial image quality assessment. U3FQ was rigorously evaluated against general IQA techniques—BRISQUE, BLINDS-II, RankIQA, and specialized FIQA methodologies like PFE, SER-FIQA, and SDD-FIQA. Results are backed up with qualitative analysis on the effectiveness of the generated quality scores through DET plots of FNMR on different age ranges, expression matches heat maps, and Expected Verification Rate (EVRC) curves on various datasets.

Abstract

The difficulty of reliably extracting characters had delayed the character recognition solutions (or OCRs) in Indian languages. Contemporary research in Indian language text recognition has shifted towards recognizing text in word or line images without requiring sub-word segmentation, leveraging Connectionist Temporal Classification (CTC) for modeling unsegmented sequences. The next challenge is the lack of public data for all these languages. And there is an immediate need to lower the entry barrier for startups or solution providers. With this in mind, (i) we introduce Mozhi dataset, a novel public dataset comprising over 1.2 million annotated word images (equivalent to approximately 120 thousand text line images) across 13 languages. (ii) We conduct a comprehensive empirical analysis of various neural network models employing CTC across 13 Indian languages. (iii) We also provide APIs for our OCR models and web-based applications that integrate these APIs to digitize Indic printed documents. We compare our model’s performance with popular publicly available OCR tools for end-to-end document image recognition. Our model outperform these OCR engines on 8 out of 13 languages.

Abstract

This paper presents a diverse compilation of Indic offline handwritten documents. Our dataset comprises 91K handwritten document images captured through unconstrained camera across thirteen Indic languages: Assamese, Bengali, Gujarati, Hindi, Kannada, Malayalam, Manipuri, Marathi, Oriya, Punjabi, Tamil, Telugu, and Urdu, contributed by 1,220 writers. This dataset encompasses 2600K words and includes 566,187 unique words featuring diverse content types, such as alphabetic and numeric. Additionally, we establish a high baseline for the proposed dataset, facilitating evaluation, benchmarking and explicitly focusing on word recognition tasks. Our findings indicate that our dataset is an effective training source for enhancing performance on respective datasets.

Abstract

The recent surge in the vehicle market has led to an alarming increase in road accidents. This underscores the critical importance of enhancing road safety measures, particularly for vulnerable road users like motorcyclists. Hence, we introduce the rider intention prediction (RIP) competition that aims to address challenges in rider safety by proactively predicting maneuvers before they occur, thereby strengthening rider safety. This capability enables the riders to react to the potential incorrect maneuvers flagged by advanced driver assistance systems (ADAS). We collect a new dataset, namely, rider action anticipation dataset (RAAD) for the competition consisting of two tasks: single-view RIP and multi-view RIP. The dataset incorporates a spectrum of traffic conditions and challenging navigational maneuvers on roads with varying lighting conditions. For the competition, we received seventy-five registrations and five team submissions for inference of which we compared the methods of the top three performing teams on both the RIP tasks: one state-space model (Mamba2) and two learning-based approaches (SVM and CNN-LSTM). The results indicate that the state-space model outperformed the other methods across the entire dataset, providing a balanced performance across maneuver classes. The SVM-based RIP method showed the second-best performance when using random sampling and SMOTE. However, the CNN-LSTM method underperformed, primarily due to class imbalance issues, particularly struggling with minority classes. This paper details the proposed RAAD dataset and provides a summary of the submissions for the RIP 2024 competition.