相关论文: PHANTOM: Polymorphic Honeytoken Adaptation with Na…
Black-box deep neural networks excel in text classification, yet their application in high-stakes domains is hindered by their lack of interpretability. To address this, we propose Text Bottleneck Models (TBM), an intrinsically…
Deep learning has been popularized by its recent successes on challenging artificial intelligence problems. One of the reasons for its dominance is also an ongoing challenge: the need for immense amounts of computational power. Hardware…
Fine-grained entity typing (FET), which assigns entities in text with context-sensitive, fine-grained semantic types, is a basic but important task for knowledge extraction from unstructured text. FET has been studied extensively in natural…
Ransomware has become one of the most serious cybersecurity threats causing major financial losses and operational disruptions worldwide.Traditional detection methods such as static analysis, heuristic scanning and behavioral analysis often…
Decompilation is foundational to binary analysis, yet conventional tools prioritize human readability over strict recompilability and verifiable runtime correctness. While recent LLM-based approaches attempt to refine decompiled pseudocode,…
We present a novel approach to tackle domain adaptation between synthetic and real data. Instead, of employing "blind" domain randomization, i.e., augmenting synthetic renderings with random backgrounds or changing illumination and…
User authentication and fraud detection face growing challenges as digital systems expand and adversaries adopt increasingly sophisticated tactics. Traditional knowledge-based authentication remains rigid, requiring exact word-for-word…
Providing AI agents with reliable long-term memory that does not hallucinate remains an open problem. Current approaches to memory for LLM agents -- sliding windows, summarization, embedding-based RAG, and flat fact extraction -- each…
A taxonomy is a hierarchical graph containing knowledge to provide valuable insights for various web applications. However, the manual construction of taxonomies requires significant human effort. As web content continues to expand at an…
Subword tokenization introduces a computational layer in language models where many distinct token sequences decode to the same surface form and preserve meaning, yet induce different internal computations. Despite this non-uniqueness,…
We propose an explainable probabilistic framework for characterizing spoofed speech by decomposing it into probabilistic attribute embeddings. Unlike raw high-dimensional countermeasure embeddings, which lack interpretability, the proposed…
Semantic communication has attracted significant interest recently due to its capability to meet the fast growing demand on user-defined and human-oriented communication services such as holographic communications, eXtended reality (XR),…
Deep research agents increasingly interleave web browsing with multi-step computation, yet existing benchmarks evaluate these capabilities in isolation, creating a blind spot in assessing real-world performance. We introduce DRBENCHER, a…
Over the years, honeypots emerged as an important security tool to understand attacker intent and deceive attackers to spend time and resources. Recently, honeypots are being deployed for Internet of things (IoT) devices to lure attackers,…
Purpose: Digital phantoms are one of the key components of virtual imaging trials (VITs) that aim to assess and optimize new medical imaging systems and algorithms. However, these phantoms vary in their voxel resolution, appearance, and…
Effective e-commerce risk management requires in-depth case investigations to identify emerging fraud patterns in highly adversarial environments. However, manual investigation typically requires analyzing the associations and couplings…
The rapid advancement of generative adversarial networks (GANs) and diffusion models has enabled the creation of highly realistic deepfake content, posing significant threats to digital trust across audio-visual domains. While unimodal…
MLLMs require high-resolution visual inputs for fine-grained tasks like document understanding and dense scene perception. However, current global resolution scaling paradigms indiscriminately flood the quadratic self-attention mechanism…
Neural speech models build deeply entangled internal representations, which capture a variety of features (e.g., fundamental frequency, loudness, syntactic category, or semantic content of a word) in a distributed encoding. This complexity…
The use of machine learning algorithms is an attractive way to produce very fast detector simulations for scattering reactions that can otherwise be computationally expensive. Here we develop a factorised approach where we deal with each…