PYSEC-2025-145

A vulnerability in the Ollama server version 0.5.11 allows a malicious user to cause a Denial of Service DoS attack by customizing the manifest content and spoofing a service. This is due to improper validation of array index access when downloading a model via the /api/pull endpoint, which can...

CVE-2025-4753

A vulnerability was found in D-Link DI-7003GV2 24.04.18D1 R68125 and classified as problematic. Affected by this issue is some unknown functionality of the file /login.data. The manipulation leads to information disclosure. The attack may be launched remotely. The exploit has been disclosed to th...

GenoArmory: a Unified Evaluation Framework for Adversarial Attacks on Genomic Foundation Models

We propose the first unified adversarial attack benchmark for Genomic Foundation Models GFMs, named GenoArmory. Unlike existing GFM benchmarks, GenoArmory offers the first comprehensive evaluation framework to systematically assess the vulnerability of GFMs to adversarial attacks. Methodologicall...

GuardReasoner-VL: Safeguarding VLMs Via Reinforced Reasoning

To enhance the safety of VLMs, this paper introduces a novel reasoning-based VLM guard model dubbed GuardReasoner-VL. The core idea is to incentivize the guard model to deliberatively reason before making moderation decisions via online RL. First, we construct GuardReasoner-VLTrain, a reasoning...

Adversarially Robust Spiking Neural Networks with Sparse Connectivity

Deployment of deep neural networks in resource-constrained embedded systems requires innovative algorithmic solutions to facilitate their energy and memory efficiency. To further ensure the reliability of these systems against malicious actors, recent works have extensively studied adversarial...

AutoRAN: Weak-To-Strong Jailbreaking of Large Reasoning Models

This paper presents AutoRAN, the first automated, weak-to-strong jailbreak attack framework targeting large reasoning models LRMs. At its core, AutoRAN leverages a weak, less-aligned reasoning model to simulate the target model's high-level reasoning structures, generates narrative prompts, and...

"Explain, Don'T Just Warn!" -- a Real-Time Framework for Generating Phishing Warnings with Contextual Cues

Anti-phishing tools typically display generic warnings that offer users limited explanation on why a website is considered malicious, which can prevent end-users from developing the mental models needed to recognize phishing cues on their own. This becomes especially problematic when these tools...

MPMA: Preference Manipulation Attack against Model Context Protocol

Model Context Protocol MCP standardizes interface mapping for large language models LLMs to access external data and tools, which revolutionizes the paradigm of tool selection and facilitates the rapid expansion of the LLM agent tool ecosystem. However, as the MCP is increasingly adopted,...

CVE-2025-22892

Uncontrolled resource consumption for some OpenVINO™ model server software maintained by IntelR before version 2024.4 may allow an unauthenticated user to potentially enable denial of service via adjacent access...

Incorrect Authorization

Overview Affected versions of this package are vulnerable to Incorrect Authorization via the ExperimentalSettings function. An attacker can exploit this issue by accessing unauthorized settings through the System Console. Note: This is only exploitable if the RestrictSystemAdmin setting is true,...

​​How the Microsoft Secure Future Initiative brings Zero Trust to life

In this blog, you'll learn more about how the Microsoft Secure Future Initiative SFI—a real-world case study on Zero Trust—aligns with Zero Trust strategies. We’ll share key updates from the April 2025 SFI progress report and practical Zero Trust guidance to help you strengthen your organization’...

On Technique Identification and Threat-Actor Attribution Using LLMs and Embedding Models

Attribution of cyber-attacks remains a complex but critical challenge for cyber defenders. Currently, manual extraction of behavioral indicators from dense forensic documentation causes significant attribution delays, especially following major incidents at the international scale. This research...

Sybil-Based Virtual Data Poisoning Attacks in Federated Learning

Federated learning is vulnerable to poisoning attacks by malicious adversaries. Existing methods often involve high costs to achieve effective attacks. To address this challenge, we propose a sybil-based virtual data poisoning attack, where a malicious client generates sybil nodes to amplify the...

Enhancing IoT Cyber Attack Detection in the Presence of Highly Imbalanced Data

Due to the rapid growth in the number of Internet of Things IoT networks, the cyber risk has increased exponentially, and therefore, we have to develop effective IDS that can work well with highly imbalanced datasets. A high rate of missed threats can be the result, as traditional machine learnin...

DataSentinel: a Game-Theoretic Detection of Prompt Injection Attacks

LLM-integrated applications and agents are vulnerable to prompt injection attacks, where an attacker injects prompts into their inputs to induce attacker-desired outputs. A detection method aims to determine whether a given input is contaminated by an injected prompt. However, existing detection...

Defending the Edge: Representative-Attention for Mitigating Backdoor Attacks in Federated Learning

Federated learning FL enhances privacy and reduces communication cost for resource-constrained edge clients by supporting distributed model training at the edge. However, the heterogeneous nature of such devices produces diverse, non-independent, and identically distributed non-IID data, making t...

SecReEvalBench: a Multi-Turned Security Resilience Evaluation Benchmark for Large Language Models

The increasing deployment of large language models in security-sensitive domains necessitates rigorous evaluation of their resilience against adversarial prompt-based attacks. While previous benchmarks have focused on security evaluations with limited and predefined attack domains, such as...

Automating Security Audit Using Large Language Model Based Agent: an Exploration Experiment

In the current rapidly changing digital environment, businesses are under constant stress to ensure that their systems are secured. Security audits help to maintain a strong security posture by ensuring that policies are in place, controls are implemented, gaps are identified for cybersecurity...

CVE-2025-47274

ToolHive is a utility designed to simplify the deployment and management of Model Context Protocol MCP servers. Due to the ordering of code used to start an MCP server container, versions of ToolHive prior to 0.0.33 inadvertently store secrets in the run config files which are used to restart...

The vulnerability of the /goform/formTcpipSetup function in D-Link DIR-618 and DIR-605L router microprogramming software allows a hacker to execute arbitrary code.

The vulnerability of the /goform/formTcpipSetup function in D-Link DIR-618 and DIR-605L router microprogramming software is related to access control errors. Exploiting this vulnerability allows a remote attacker to execute arbitrary code...