The paper introduces FigSIM, the first fine-grained dataset for analyzing suicide memes, which is used to benchmark models across tasks like suicide severity and figurative language detection.

This study analyzed the online exposure of Thai National Identification Numbers and other sensitive personal data, revealing over 1.2 million records, primarily originating from government websites, w…

The paper introduces FBHM, a new benchmark for hateful memes, and proposes LSV, a steering vector method that significantly improves VLM performance by addressing the generalization gap.

The paper introduces the $\alpha$-Wasserstein mechanism to achieve Rényi Pufferfish Privacy using Laplace and Gaussian noise, demonstrating that it generalizes existing privacy frameworks and reduces…

QSignAI is an open-source platform that integrates quantum-randomness-seeded identity signatures into a conversational AI social messaging system, demonstrating a practical bidirectional link between…

This systematic review analyzes the current state of SMS phishing (smishing) attacks and defenses, organizing existing research into four pillars to identify gaps and propose future mitigation strateg…

This paper presents methods for ranking and unranking permutations avoiding a pattern of length three in lexicographic or colexicographic order.

The paper introduces FormInv, a measurement protocol that reveals significant semantic inconsistencies in existing mathematical reasoning benchmarks, showing that standard accuracy metrics fail to cap…

This paper introduces a Hybrid Mixture-of-Experts (HybridMoE) framework and a specialized corpus (Varnika) to significantly improve language models' ability to understand and retain figurative, cultur…

The paper introduces STARFISH, a novel healing method that efficiently recovers significant accuracy in heavily pruned neural networks by optimizing the pruned model to match the original network's in…

The paper introduces a kill-chain canary methodology to diagnose prompt injection vulnerabilities across multi-stage LLM pipelines, revealing that write-node placement and document format are critical…

ParikkhaChain proposes a novel blockchain framework to manage the entire lifecycle of onsite academic examinations, ensuring transparency, eliminating bias, and preserving student privacy.

This paper investigates a novel security vulnerability where imperceptible branding hints can be injected into images and subsequently re-rendered onto new objects by generative AI models, proposing b…

MaskForge is a novel, adaptive, black-box attack framework that significantly improves jailbreaking diffusion large language models (dLLMs) by treating red-teaming as an optimized search over reusable…

The paper introduces 5WBENCH, a new benchmark for causal unlearning, and proposes MAAT, a novel three-phase framework that achieves high forgetting and high retention specifically on complex 'Why'-typ…

The paper proves that the reversible elementary second order cellular automaton rule 115 is periodic when started on finite initial configurations.

This paper analyzes the computational complexity of evaluating recurrent functions, showing that the complexity depends heavily on how the input offsets are encoded and the structure of the recurrence…

The paper proposes TAGBD, a graph-aware backdoor attack that demonstrates that inconspicuous poison text alone can reliably compromise text-attributed graph learning systems.

Clark Hash is a stateless, deterministic quantization method that significantly reduces the storage size of neural embeddings while maintaining high accuracy for cosine similarity search.