Related papers: CVPL: A Geometric Framework for Post-Hoc Linkage R…

As interconnected systems proliferate, safeguarding complex infrastructures against an escalating array of cyber threats has become an urgent challenge. The increasing number of vulnerabilities, combined with resource constraints, makes…

Large Language Models (LLMs) have gained significant attention but also raised concerns due to the risk of misuse. Jailbreak prompts, a popular type of adversarial attack towards LLMs, have appeared and constantly evolved to breach the…

We present the 1st-place solution to the ACCIDENT challenge at the CVPR 2026 AUTOPILOT Workshop, which asks for zero-shot prediction of accident timing, impact centroid, and collision type from CCTV footage. On a frozen…

Fine-tuning vision-language models (VLMs) with abundant unlabeled data recently has attracted increasing attention. Existing methods that resort to the pseudolabeling strategy would suffer from heavily incorrect hard pseudolabels when VLMs…

The recently proposed FixMatch achieved state-of-the-art results on most semi-supervised learning (SSL) benchmarks. However, like other modern SSL algorithms, FixMatch uses a pre-defined constant threshold for all classes to select…

Privacy-Preserving Record Linkage (PPRL) supports the integration of sensitive information from multiple datasets, in particular the privacy-preserving matching of records referring to the same entity. PPRL has gained much attention in many…

The Common Vulnerabilities and Exposures (CVE) are pivotal information for proactive cybersecurity measures, including service patching, security hardening, and more. However, CVEs typically offer low-level, product-oriented descriptions of…

Common Vulnerability and Exposure (CVE) records are fundamental to cybersecurity, offering unique identifiers for publicly known software and system vulnerabilities. Each CVE is typically assigned a Common Vulnerability Scoring System…

Vertical federated learning (VFL) is an emerging paradigm that allows different parties (e.g., organizations or enterprises) to collaboratively build machine learning models with privacy protection. In the training phase, VFL only exchanges…

Semi-supervised action recognition is a challenging but important task due to the high cost of data annotation. A common approach to this problem is to assign unlabeled data with pseudo-labels, which are then used as additional supervision…

Video Correlation Learning (VCL), which aims to analyze the relationships between videos, has been widely studied and applied in various general video tasks. However, applying VCL to instructional videos is still quite challenging due to…

The integration of LLMs into vulnerability detection (VD) has shifted the field toward more interpretable and context-aware analysis. While post-training techniques have shown promise in general coding tasks, their systematic application to…

Correlation clustering is a central problem in unsupervised learning, with applications spanning community detection, duplicate detection, automated labelling and many more. In the correlation clustering problem one receives as input a set…

Complementary-label learning (CLL) is a weakly-supervised learning paradigm that aims to train a multi-class classifier using only complementary labels, which indicate classes to which an instance does not belong. Despite numerous…

We establish Multilayer Correlation Clustering, a novel generalization of Correlation Clustering to the multilayer setting. In this model, we are given a series of inputs of Correlation Clustering (called layers) over the common set $V$ of…

Learning knowledge representation is an increasingly important technology applicable in many domain-specific machine learning problems. We discuss the effectiveness of traditional Link Prediction or Knowledge Graph Completion evaluation…

Multimodal Large Language Models (MLLMs) have demonstrated impressive capabilities in cross-modal understanding, but remain vulnerable to adversarial attacks through visual inputs despite robust textual safety mechanisms. These…

Cyber-security vulnerabilities are usually published in form of short natural language descriptions (e.g., in form of MITRE's CVE list) that over time are further manually enriched with labels such as those defined by the Common…

This paper addresses a critical challenge in cybersecurity: the gap between vulnerability information represented by Common Vulnerabilities and Exposures (CVEs) and the resulting cyberattack actions. CVEs provide insights into…

Correlation Clustering is a powerful graph partitioning model that aims to cluster items based on the notion of similarity between items. An instance of the Correlation Clustering problem consists of a graph $G$ (not necessarily complete)…