The vulnerability of Ollama’s system for running and managing large language models lies in its lack of proper input data validation, allowing attackers to execute arbitrary code.

The vulnerability of Ollama’s system for running and managing large language models is related to insufficient validation of input data. Exploiting this vulnerability could allow a remote attacker to execute arbitrary code...

Cascading and Proxy Membership Inference Attacks

A Membership Inference Attack MIA assesses how much a trained machine learning model reveals about its training data by determining whether specific query instances were included in the dataset. We classify existing MIAs into adaptive or non-adaptive, depending on whether the adversary is allowed...

EdgeAgentX-DT: Integrating Digital Twins and Generative AI for Resilient Edge Intelligence in Tactical Networks

We introduce EdgeAgentX-DT, an advanced extension of the EdgeAgentX framework that integrates digital twin simulations and generative AI-driven scenario training to significantly enhance edge intelligence in military networks. EdgeAgentX-DT utilizes network digital twins, virtual replicas...

SDD: Self-Degraded Defense against Malicious Fine-Tuning

Open-source Large Language Models LLMs often employ safety alignment methods to resist harmful instructions. However, recent research shows that maliciously fine-tuning these LLMs on harmful data can easily bypass these safeguards. To counter this, we theoretically uncover why malicious fine-tuni...

Information Exposure

Overview Affected versions of this package are vulnerable to Information Exposure via the q URL parameter in the /api/v2.0/users endpoint. An attacker can retrieve sensitive password hash and salt values by abusing the filtering capability to extract this information character by character. Note:...

Subliminal Learning in AIs

Today's freaky LLM behavior: We study subliminal learning, a surprising phenomenon where language models learn traits from model-generated data that is semantically unrelated to those traits. For example, a "student" model learns to prefer owls when trained on sequences of numbers generated by a...

Enhancing IoT Intrusion Detection Systems through Adversarial Training

The augmentation of Internet of Things IoT devices transformed both automation and connectivity but revealed major security vulnerabilities in networks. We address these challenges by designing a robust intrusion detection system IDS to detect complex attacks by learning patterns from the...

PrompTrend: Continuous Community-Driven Vulnerability Discovery and Assessment for Large Language Models

Static benchmarks fail to capture LLM vulnerabilities emerging through community experimentation in online forums. We present PrompTrend, a system that collects vulnerability data across platforms and evaluates them using multidimensional scoring, with an architecture designed for scalable...

OneShield -- the Next Generation of LLM Guardrails

The rise of Large Language Models has created a general excitement about the great potential for a myriad of applications. While LLMs offer many possibilities, questions about safety, privacy, and ethics have emerged, and all the key actors are working to address these issues with protective...

CVE-2025-4395

Medtronic MyCareLink Patient Monitor has a built-in user account with an empty password, which allows an attacker with physical access to log in with no password and access modify system functionality. This issue affects MyCareLink Patient Monitor models 24950 and 24952: before June 25, 2025...

CVE-2025-4394 Medtronic MyCareLink Patient Monitor Unencrypted Filesystem Vulnerability

Medtronic MyCareLink Patient Monitor uses an unencrypted filesystem on internal storage, which allows an attacker with physical access to read and modify files. This issue affects MyCareLink Patient Monitor models 24950 and 24952: before June 25, 2025...

CVE-2025-4394

Medtronic MyCareLink Patient Monitor uses an unencrypted filesystem on internal storage, which allows an attacker with physical access to read and modify files. This issue affects MyCareLink Patient Monitor models 24950 and 24952: before June 25, 2025...

CVE-2025-4393 Medtronic MyCareLink Patient Monitor Deserialization Vulnerability

Medtronic MyCareLink Patient Monitor has an internal service that deserializes data, which allows a local attacker to interact with the service by crafting a binary payload to crash the service or elevate privileges. This issue affects MyCareLink Patient Monitor models 24950 and 24952: before Jun...

CVE-2025-4393

Medtronic MyCareLink Patient Monitor has an internal service that deserializes data, which allows a local attacker to interact with the service by crafting a binary payload to crash the service or elevate privileges. This issue affects MyCareLink Patient Monitor models 24950 and 24952: before Jun...

CVE-2025-4393

CVE-2025-4393 affects Medtronic MyCareLink Patient Monitor, specifically models 24950 and 24952 . The root cause is an internal service that deserializes data, enabling a local attacker to interact with the service by crafting a binary payload, potentially causing a crash or privilege escalation ...

Auto-SGCR: Automated Generation of Smart Grid Cyber Range Using IEC 61850 Standard Models

Digitalization of power grids have made them increasingly susceptible to cyber-attacks in the past decade. Iterative cybersecurity testing is indispensable to counter emerging attack vectors and to ensure dependability of critical infrastructure. Furthermore, these can be used to evaluate...

Scout: Leveraging Large Language Models for Rapid Digital Evidence Discovery

Recent technological advancements and the prevalence of technology in day to day activities have caused a major increase in the likelihood of the involvement of digital evidence in more and more legal investigations. Consumer-grade hardware is growing more powerful, with expanding memory and...

Enabling Cyber Security Education through Digital Twins and Generative AI

Digital Twins DTs are gaining prominence in cybersecurity for their ability to replicate complex IT Information Technology, OT Operational Technology, and IoT Internet of Things infrastructures, allowing for real time monitoring, threat analysis, and system simulation. This study investigates how...

EX-NIDS: a Framework for Explainable Network Intrusion Detection Leveraging Large Language Models

This paper introduces eX-NIDS, a framework designed to enhance interpretability in flow-based Network Intrusion Detection Systems NIDS by leveraging Large Language Models LLMs. In our proposed framework, flows labelled as malicious by NIDS are initially processed through a module called the Promp...

When LLMs Copy to Think: Uncovering Copy-Guided Attacks in Reasoning LLMs

Large Language Models LLMs have become integral to automated code analysis, enabling tasks such as vulnerability detection and code comprehension. However, their integration introduces novel attack surfaces. In this paper, we identify and investigate a new class of prompt-based attacks, termed...