Important: Red Hat Security Advisory: Red Hat Enterprise Linux AI 3.3.1

Red Hat Enterprise Linux AI 3.3.1 is now available. Red Hat® Enterprise Linux® AI is a foundation model platform to seamlessly develop, test, and run Granite family large language models LLMs for enterprise applications...

Important: Red Hat Security Advisory: Red Hat Enterprise Linux AI 3.3.1

Red Hat Enterprise Linux AI 3.3.1 is now available. Red Hat® Enterprise Linux® AI is a foundation model platform to seamlessly develop, test, and run Granite family large language models LLMs for enterprise applications...

A Sociotechnical, Practitioner-Centered Approach to Technology Adoption in Cybersecurity Operations: An LLM Case

Technology for security operations centers SOCs has a storied history of slow adoption due to concerns about trust and reliability. These concerns are amplified with artificial intelligence, particularly large language models LLMs, which exhibit issues such as hallucinations and inconsistent...

Risk Models As Mediating Artifacts: A Postphenomenological Analysis of the CIIM Framework in Cybersecurity Practice

This article applies postphenomenological theory to the field of cybersecurity risk management, arguing that formal risk models function as mediating artifacts that shape how security practitioners or analysts perceive, interpret, and act on threats. Based on Don Ihde's taxonomy on human-technolo...

📄 Keras 3.13.0 Malicious ML Model Server HDF5 Shape Bomb

This script is a Flask-based web server that distributes .keras machine learning model files, but it is designed in a malicious way for security research/testing scenarios. The main idea is a denial of service via memory exhaustion, where generated Keras models contain artificially declared...

CVE-2025-70994

Yadea T5 Electric Bicycles models manufactured in/after 2024 have a weak authentication mechanism in their keyless entry system. The system utilizes the EV1527 fixed-code RF protocol without implementing rolling codes or cryptographic challenge-response mechanisms. This is vulnerable to signal...

AutoRISE: Agent-Driven Strategy Evolution for Red-Teaming Large Language Models

Automated red-teaming methods for large language models typically optimize attack prompts within a fixed, human-designed strategy, leaving the attack strategy itself unchanged. We instead optimize the strategy. We propose AutoRISE, a method that searches over executable attack programs rather tha...

Transient Turn Injection: Exposing Stateless Multi-Turn Vulnerabilities in Large Language Models

Large language models LLMs are increasingly integrated into sensitive workflows, raising the stakes for adversarial robustness and safety. This paper introduces Transient Turn InjectionTTI, a new multi-turn attack technique that systematically exploits stateless moderation by distributing...

EUVD-2026-24752

A flaw was found in InstructLab. The linuxtrain.py script hardcodes trustremotecode=True when loading models from HuggingFace. This allows a remote attacker to achieve arbitrary Python code execution by convincing a user to run ilab train/download/generate with a specially crafted malicious model...

Inclusion of Functionality from Untrusted Control Sphere

Overview instructlab is a Core package for interacting with InstructLab Affected versions of this package are vulnerable to Inclusion of Functionality from Untrusted Control Sphere via default trustremotecode=True for loading models from HuggingFacein in linuxtrain.py file. An attacker can execut...

CVE-2026-6859

A flaw was found in InstructLab. The linuxtrain.py script hardcodes trustremotecode=True when loading models from HuggingFace. This allows a remote attacker to achieve arbitrary Python code execution by convincing a user to run ilab train/download/generate with a specially crafted malicious model...

CVE-2026-6859

A flaw was found in InstructLab. The linuxtrain.py script hardcodes trustremotecode=True when loading models from HuggingFace. This allows a remote attacker to achieve arbitrary Python code execution by convincing a user to run ilab train/download/generate with a specially crafted malicious model...

CVE-2026-6859 Instructlab: instructlab: arbitrary code execution due to hardcoded `trust_remote_code=true`

A flaw was found in InstructLab. The linuxtrain.py script hardcodes trustremotecode=True when loading models from HuggingFace. This allows a remote attacker to achieve arbitrary Python code execution by convincing a user to run ilab train/download/generate with a specially crafted malicious model...

llm-security-lab

LLM Security Lab Laboratoire de sécurité pour application...

TL-RL-FusionNet: An Adaptive and Efficient Reinforcement Learning-Driven Transfer Learning Framework for Detecting Evolving Ransomware Threats

Modern ransomware exhibits polymorphic and evasive behaviors by frequently modifying execution patterns to evade detection. This dynamic nature disrupts feature spaces and limits the effectiveness of static or predefined models. To address this challenge, we propose TL-RL-FusionNet, a reinforceme...

AVISE: Framework for Evaluating the Security of AI Systems

As artificial intelligence AI systems are increasingly deployed across critical domains, their security vulnerabilities pose growing risks of high-profile exploits and consequential system failures. Yet systematic approaches to evaluating AI security remain underdeveloped. In this paper, we...

CVE-2026-41131 OpenFGA has Improper Policy Enforcement

OpenFGA is an authorization/permission engine built for developers. Prior to version 1.14.1, in specific scenarios, models using conditions with caching enabled can result in two different check requests producing the same cache key. This could result in OpenFGA reusing an earlier cached result f...

DP-FlogTinyLLM: Differentially Private Federated Log Anomaly Detection Using Tiny LLMs

Modern distributed systems generate massive volumes of log data that are critical for detecting anomalies and cyber threats. However, in real world settings, these logs are often distributed across multiple organizations and cannot be centralized due to privacy and security constraints. Existing...

Involuntary In-Context Learning: Exploiting Few-Shot Pattern Completion to Bypass Safety Alignment in GPT-5.4

Safety alignment in large language models relies on behavioral training that can be overridden when sufficiently strong in-context patterns compete with learned refusal behaviors. We introduce Involuntary In-Context Learning IICL, an attack class that uses abstract operator framing with few-shot...

Evaluating LLM-Generated Obfuscated XSS Payloads for Machine Learning-Based Detection

Cross-site scripting XSS remains a persistent web security vulnerability, especially because obfuscation can change the surface form of a malicious payload while preserving its behavior. These transformations make it difficult for traditional and machine learning-based detection systems to reliab...