Abstract

Understanding what makes a video memorable has important applications in advertising or education technology. Towards this goal, we investigate spatio-temporal attention mechanisms underlying video memorability. Different from previous works that fuse multiple features, we adopt a simple CNN+Transformer architecture that enables analysis of spatio-temporal attention while matching state-of-the-art (SoTA) performance on video memorability prediction. We compare model attention against human gaze fixations collected through a small-scale eye-tracking study where humans perform the video memory task. We uncover the following insights: (i) Quantitative saliency metrics show that our model, trained only to predict a memorability score, exhibits similar spatial attention patterns to human gaze, especially for more memorable videos. (ii) The model assigns greater importance to initial frames in a video, mimicking human attention patterns. (iii) Panoptic segmentation reveals that both (model and humans) assign a greater share of attention to things and less attention to stuff as compared to their occurrence probability.

Abstract

Existing research suggests that mountain and plain societies differ due to geographical factors and this study tests this hypothesis by examining the political dynamics of these two types of societies. We perform a quantitative analysis, followed by an exploration of possible qualitative explanations. Duverger’s Law states that single-member plurality electoral systems typically result in two-party dominance. However, India is a well-known exception in the literature due to strong regional parties as it deviates from this trend. For the quantitative analysis, central election data from the Election Commission of India from 1977 to 2014 is used to conduct a temporal analysis. Laakso and Taagepera’s Effective Number of Parties (ENP) metric is calculated by squaring each party’s share of votes or seats, summing these squares and taking the reciprocal. It is used to find the effective political parties that exist in a district considering both their number and vote share. According to Duverger’s Law, the ENP should ideally converge to 2 over time. This analysis reveals that in plains the ENP values are increasing over time (suggesting divergence) whereas mountain regions are gradually converging towards a two-party system. We conduct a one-way ANOVA for each election by grouping the ENP values for mountain and plain districts separately. A statistically significant difference between the ENP values of mountain and plain districts across all elections. For qualitative analysis, James Scott’s concept of Zomia along with different ideas of Zomia presented by Schendel, Schneiderman are discussed and how they might offer an explanation for the observation. Ultimately, the study sheds light on the socio-political distinctions between mountainous and plain regions in India, supporting historical and sociological theories that suggest mountain societies preserve unique political traits.

Abstract

The rapid evolution of Large Language Models (LLMs) have opened new possibilities in automating tasks across the software developing life cycle, including test case generation This paper presents a comparative analysis of six LLMs in the context of generating test cases for technical requirements written in natural language (in this case English). We compare publicly available general purpose LLMs viz., BARD, ChatGPT3.5, Claude, Gemini, ChatGPT4.o (Omni) and Llama3. The generated test cases are tested against a Simulink model created for the corresponding set of requirements. The coverage metrics thus generated are used for a quantitative comparison of the LLMs.

Abstract

Evaluating machine translation (MT) systems for low-resource languages has long been a challenge due to the limited availability of evaluation metrics and resources. As a result, researchers in this space have relied primarily on lexical-based metrics like BLEU, TER, and ChrF, which lack semantic evaluation. In this first-of-its-kind work, we propose a novel pivot-based evaluation framework that addresses these limitations; after translating low-resource language outputs into a related high-resource language, we leverage advanced neural and embedding-based metrics for more meaningful evaluation. Through a series of experiments using five low-resource languages: Assamese, Manipuri, Kannada, Bhojpuri, and Nepali, we demonstrate how this method extends the coverage of both lexical-based and embedding-based metrics, even for languages not directly supported by advanced metrics. Our results show that the differences between direct and pivot-based evaluation scores are minimal, proving that this approach is a viable and effective solution for evaluating translations in endangered and low-resource languages. This work paves the way for more inclusive, accurate, and scalable MT evaluation for underrepresented languages, marking a significant step forward in this under-explored area of research.

Abstract

The significant improvements in point cloud representation learning have increased its applicability in many real-life applications, resulting in the need for lightweight, better-performing models. One widely proposed efficient method is knowledge distillation, where a lightweight model uses knowledge from large models. Very few works exist on distilling the knowledge for point clouds. Most of the work focuses on cross-modal-based approaches that make the method expensive to train. This paper proposes PointKAD, an adversarial knowledge distillation framework for point cloud-based tasks. PointKAD includes adversarial feature distillation and response distillation with the help of discriminators to extract and distill the representation of feature maps and logits. We conduct extensive experimental studies on both synthetic (ModelNet40) and real (ScanObjectNN) datasets to show that PointKAD achieves state-of-the-art results compared to the existing knowledge distillation methods for point cloud classification. Additionally, we present results on the part segmentation task, highlighting the efficacy of the PointKAD framework. Our experiments further reveal that PointKAD is capable of transferring knowledge across different tasks and datasets, showcasing its versatility. Furthermore, we demonstrate that PointKAD can be applied to a cross-modal training setup, achieving competitive performance with cross-modal-based point cloud methods for classification.

Abstract

Tornado Cash is a decentralized application (dApp) that runs on Ethereum Virtual Machine (EVM) compatible networks to enhance users’ privacy in terms of user transaction history over the blockchain. This dApp achieves its goal by enabling users to deposit currencies into designated pools and subsequently withdraw them, severing the link between depositor and withdrawer addresses. At deposit time, Tornado Cash communicates to users the level of privacy they will benefit from (anonymity set) by depositing currencies into one of its pools. Existing analyses have indicated discrepancies between the claimed anonymity set and the actual level of privacy provided, primarily attributed to users’ incorrect utilization of the dApp. This paper explores the road towards a new way to challenge the dApp’s proposed anonymity set by examining wallet fingerprints, a factor not directly related to user behavior within the application. The findings of this research shed light on the potential for creating links between clusters of users in TC according to the new proposed approach and raise a privacy concern within the Ethereum network, resulting in 13203 transactions, over 66948, linkable to the wallet used to initialize them.

Abstract

A Completely Automated Public Turing Test to Tell Computers and Humans Apart (CAPTCHA) is one of the primary barriers between notorious bots and legitimate human users. However, advancements in Artificial Intelligence (AI) have enabled malicious bots to circumvent CAPTCHA challenges effectively. As a result, several types of CAPTCHA have been rendered ineffective. In this work, we introduce Swiss Cheese CAPTCHA, a novel sensor-based solution designed to be easily solvable by humans while presenting multiple obstructions for bots (similar to the Swiss Cheese Model) even when the sensor outputs can be predicted and interfered with. We leverage a range of human cognitive abilities and Generic Sensor API in modern devices to provide robust protection against automated attacks by making it more computationally expensive for bots to produce a valid answer within a stipulated time. We conducted two user studies to assess our proposal’s effectiveness: one involving 116 participants to assess the likability and improvise the design, and the other, with 107 participants, to investigate the impact of improvised design changes on cognitive abilities. Our results from these studies show an average completion time of 4.76 seconds and 6.12 seconds, with a success rate of 90.3% and 83.25%, respectively. By analyzing the 2141 resultant trajectories from both user studies, we assess the learnability, error recovery rate, efficiency, and satisfaction of users using the scheme. Finally, we devise an automated attack against our proposal to analyze its security in the real world; we find the probability of attack success is low. We also make our dataset available for further research.

Abstract

We introduce MoRAG, a novel multi-part fusion based retrieval-augmented generation strategy for text-based human motion generation. The method enhances motion diffusion models by leveraging additional knowledge obtained through an improved motion retrieval process. By effectively prompting large language models (LLMs), we address spelling errors and rephrasing issues in motion retrieval. Our approach utilizes a multi-part retrieval strategy to improve the generalizability of motion retrieval across the language space. We create diverse samples through the spatial composition of the retrieved motions. Furthermore, by utilizing low-level, part-specific motion information, we can construct motion samples for unseen text descriptions. Our experiments demonstrate that our framework can serve as a plug-and-play module, improving the performance of motion diffusion models. Code, pretrained models and sample videos will be made available at: https://motionrag.github.io/

Abstract

Moving Target Defense (MTD) has emerged as a proactive and dynamic framework to counteract evolving cyber threats. Traditional MTD approaches often rely on assumptions about the attacker’s knowledge and behavior. However, real-world scenarios are inherently more complex, with adaptive attackers and limited prior knowledge of their payoffs and intentions. This paper introduces a novel approach to MTD using a Markov Decision Process (MDP) model that does not rely on predefined attacker payoffs. Our framework integrates the attacker’s real-time responses into the defender’s MDP using a dynamic Bayesian Network. By employing a factored MDP model, we provide a comprehensive and realistic representation of the system and its dependencies. We also incorporate incremental updates to an attack response predictor as new data emerges, ensuring an adaptive and robust defense mechanism. Additionally, we consider the costs of switching configurations in MTD, integrating them into the reward structure to balance execution and defense costs. We first highlight the challenges of the problem through a theoretical negative result on regret. However, our empirical evaluations, conducted in network and web application settings, demonstrate the framework’s effectiveness in environments characterized by high uncertainty and dynamically changing attack surfaces.

Abstract

Text driven diffusion models have shown remarkable capabilities in editing images. However, when editing 3D scenes, existing works mostly rely on training a NeRF for 3D editing. Recent NeRF editing methods leverages edit operations by deploying 2D diffusion models and project these edits into 3D space. They require strong positional priors alongside text prompt to identify the edit location. These methods are operational on small 3D scenes and are more generalized to particular scene. They require training for each specific edit and cannot be exploited in real-time edits. To address these limitations, we propose a novel method, FreeEdit, to make edits in training free manner using mesh representations as a substitute for NeRF. Training-free methods are now a possibility because of the advances in foundation model’s space. We leverage these models to bring a training-free alternative and introduce solutions for insertion, replacement and deletion. We consider insertion, replacement and deletion as basic blocks for performing intricate edits with certain combinations of these operations. Given a text prompt and a 3D scene, our model is capable of identifying what object should be inserted/replaced or deleted and location where edit should be performed. We also introduce a novel algorithm as part of FreeEdit to find the optimal location on grounding object for placement. We evaluate our model by comparing it with baseline models on a wide range of scenes using quantitative and qualitative metrics and showcase the merits of our method with respect to others.