Related papers: TIPS: Threat Actor Informed Prioritization of Appl…
As AI agents become increasingly autonomous and capable, ensuring their security against vulnerabilities such as prompt injection becomes critical. This paper explores the use of information-flow control (IFC) to provide security guarantees…
This study evaluates the application of predictive analytics for real-time cyber-attack detection and response, focusing on how statistical and machine learning methods can improve decision-making in Security Operations Centers (SOCs).…
Typographic attacks exploit multi-modal systems by injecting text into images, leading to targeted misclassifications, malicious content generation and even Vision-Language Model jailbreaks. In this work, we analyze how CLIP vision encoders…
Contrastive Language-Image Pre-training (CLIP) models have demonstrated remarkable performance in zero-shot classification tasks, yet their efficacy in handling complex multi-object scenarios remains challenging. This study presents a…
Discrete image tokenizers encode visual inputs as sequences of tokens from a finite vocabulary and are gaining popularity in multimodal systems, including encoder-only, encoder-decoder, and decoder-only models. However, unlike CLIP…
Front-line police officers often categorize all police call reported cases of Telecom Fraud into 14 subcategories to facilitate targeted prevention measures, such as precise public education. However, the associated data is characterized by…
Sequential Recommendation (SR) predicts users next interactions by modeling the temporal order of their historical behaviors. Existing approaches, including traditional sequential models and generative recommenders, achieve strong…
This paper presents a novel method to enhance the reliability of image classification models during deployment in the face of transient hardware errors. By utilizing enriched text embeddings derived from GPT-3 with question prompts per…
Face recognition networks encode information about sensitive attributes while being trained for identity classification. Such encoding has two major issues: (a) it makes the face representations susceptible to privacy leakage (b) it appears…
Named Entity Recognition (NER) is a key component in industrial information extraction pipelines, where systems must satisfy strict latency and throughput constraints in addition to strong accuracy. State-of-the-art NER accuracy is often…
Modern language models have enabled the development of agentic systems that achieve strong performance on reasoning-intensive tasks. Unfortunately, this has come with a security cost; these systems are vulnerable to prompt injection, a…
Deceptive patterns are design practices embedded in digital platforms to manipulate users, representing a widespread and long-standing issue in the web and mobile software development industry. Legislative actions highlight the urgency of…
Understanding the modus operandi of adversaries aids organizations in employing efficient defensive strategies and sharing intelligence in the community. This knowledge is often present in unstructured natural language text within threat…
Predictive monitoring is a subfield of process mining that aims to predict how a running case will unfold in the future. One of its main challenges is forecasting the sequence of activities that will occur from a given point in time --…
An Intrusion Detection System (IDS) to secure computer networks reports indicators for an attack as alerts. However, every attack can result in a multitude of IDS alerts that need to be correlated to see the full picture of the attack. In…
Many important security properties can be formulated in terms of flows of tainted data, and improved taint analysis tools to prevent such flows are of critical need. Most existing taint analyses use whole-program static analysis, leading to…
This paper introduces a novel approach to person identification using hand images, designed specifically for criminal investigations. The method is particularly valuable in serious crimes such as sexual abuse, where hand images are often…
Transformer-based NLP models are powerful but have high computational costs that limit deployment. Finetuned encoder-decoder models are popular in specialized domains and can outperform larger more generalized decoder-only models, such as…
The monitoring of individuals/objects has become increasingly possible in recent years due to the convenience of integrated cameras in many devices. Due to the important moments or activities of people captured by these devices, it has made…
A wide range of computer vision algorithms rely on identifying sparse interest points in images and establishing correspondences between them. However, only a subset of the initially identified interest points results in true…