Important: Red Hat Security Advisory: Red Hat Multiarch Tuning 1.3.4

The 1.3.4 release of the Red Hat Multiarch Tuning Operator. For more details, see product documentation in the references section. Enhancements: With this update, MTO has been updated to use go version 1.26.7. Bug Fixes: Previously, deleting a ClusterPodPlacementConfig object immediately after...

Benchmarking LLMs for Threat Level Determination

The fast progress of large language models LLMs opens new opportunities in the management of cyber threat intelligence, but their reliability for operational tasks remains unclear. In this work, we benchmark LLMs on the task of threat level determination. First, we construct a curated dataset...

hate_crack v2.36.1

/ | \ / | \ \ | | / \ \ / \ / \ /\ \ \ / | |/ / \ Y // | | \ / \ | | // \ | \ /|| /\ | \ / / // / / / / Installation Installing from source is the only supported path. hatecrack is not distributed on PyPI: pip install hate-crack resolves to a 0.0.0 placeholder that fails on purpose...

HiveTraceGuard-Pro: A Compact Generative Guardrail for Prompt Injection, Jailbreaks, and Adversarial Obfuscation

Production LLMs must handle inputs that attempt to override system instructions, bypass safety policies or elicit harmful responses. A common mitigation is a separate guardrail model. Existing reports, however, provide little evidence on Russian prompt injection or Russian surface obfuscation. We...

Hidden Threat in Synthetic Data: Covert Targeted Bias Injection through Benign Text

Synthetic data is increasingly used to train large language models LLMs, yet its security implications remain poorly understood. Prior work on subliminal learning suggests that models can inherit behavioral traits from seemingly unrelated training data. In this work, we investigate whether such...

Answer Is Cheap, Show Me the Evidence! Augmenting Automated Vulnerability Assessment with Evidence

Software vulnerability SV assessment helps prioritize remediation by characterizing reported vulnerabilities. Existing automated methods predict assessment results from SV reports SVRs, but often overlook information in rich text, such as screenshots and code snippets, as well as contextual...

From Noise to Signal: Improving Security Log Anomaly Detection Using LLMs with Endpoint-Specific Logs

Existing approaches to anomalous behaviour log detection, such as Wazuh rely primarily on predefined detection rules, while statistical anomaly detection approaches such as OpenSearch identify deviations from previously observed behavioural patterns. Recent research has investigated LLMs for log...

Improving LLM-Based SSH Honeypots through Prompting and Fine-Tuning

LLM-based SSH honeypots often use closed cloud LLMs because they give strong shell realism, but cloud models create deployment problems. These include no stable versioning, provider-side changes, attacker-driven cost, and model decommissioning. Local open-weight models avoid these problems, but...

CVE-2026-61634

The RabbitMQ Java client library allows Java and JVM-based applications to connect to and interact with RabbitMQ nodes. Prior to 5.33.0, the AMQP connection tuning path records the negotiated AMQP framemax value, but src/main/java/com/rabbitmq/client/impl/SocketFrameHandler.java and...

Backdoor Decontamination Dynamics in LLM Agents

Open-weight LLM agents are vulnerable to backdoors installed during fine-tuning, which may be undetectable if the trigger conditions are never met during testing. Assuming defenders do not know the existing trigger, they cannot unlearn it directly. One decontamination strategy is to install a kno...

C-RE-ACT: Causal RE-ACTing Agent for O-RAN Forensic Triage

The shift to O-RAN architectures marks a turning point in cellular security, where increased openness and modularity directly translate into a broader attack surface. Among the security threats cataloged by the O-RAN Alliance Working Group 11, performance-degradation attacks constitute the larges...

Find Before You Fine-Tune: A Diagnostic Study of Small LLMs for Cybersecurity QA

Large Language Models LLMs are increasingly fine-tuned for critical-domain Question-Answering QA, yet choosing which small model to adapt, before paying the cost of adaptation, remains difficult. Fine-tuning can improve domain alignment, but it may also erode prior knowledge, weaken...

Beware What You Autocomplete: Forensic Attribution of Backdoored Code Completions

Large language models have enabled powerful code completion systems that assist developers by predicting subsequent lines of code. However, these models remain vulnerable to backdoor attacks, where malicious fine-tuning data covertly implants unsafe behaviors. Despite advances in defensive...

Decomposing Memorization Reduction in Privacy-Preserving Fine-Tuning of SLMs for CSIRTs

CSIRTs increasingly fine tune language models on vulnerability scan records, but these records expose internal network topology and create privacy risks under regulations such as GDPR and LGPD. We present the first empirical study of how DP SGD and HMAC pseudonymization interact when fine tuning...

Inherited Circuits, Learned Semantics: How Fine-Tuning Creates Evasion Vulnerabilities Invisible to Standard Evaluation

LLMs fine-tuned for security classification are usually evaluated on held-out examples from the same distribution as their training data. We show that this can miss vulnerabilities introduced by fine-tuning itself: models can learn token-level indicator semantics that preserve canonical accuracy...

Astra Linux – Vulnerability in Linux 6.12

In the Linux kernel, the following vulnerability has been resolved: net/rds: Fixed a circular locking dependency in rdstcptune syzbot reported a circular locking dependency in rdstcptune, where sknetrefcntupgrade is called while holding the socket lock:...

Assessing Automated Prompt Injection Attacks in Agentic Environments

Indirect prompt injection poses a critical threat to LLM agents that interact with untrusted external data, yet automated attack methods--proven effective for jailbreaking--remain underexplored in realistic agentic settings. We present a comprehensive empirical evaluation of automated prompt...

Empirical Evaluation of Large Language Models for Migration of Code Fragments to Post-Quantum Cryptography

The transition to post-quantum cryptography PQC requires not only replacing vulnerable cryptographic primitives, but also refactoring the surrounding software logic. While existing PQC migration frameworks provide organizational guidance, practical code-level remediation remains largely manual an...

Gate AI: LLM Security Benchmark Evaluation Methodology and Results

Published evaluations of prompt-injection and jailbreak detectors for Large Language Models often suffer from two systematic weaknesses: per-dataset threshold tuning and undisclosed operating points. We describe an evaluation harness that addresses both. The detector under evaluation is scored...

Patcher: Post-Hoc Patching of Backdoored Large Language Models

Large language models remain vulnerable to jailbreak backdoor attacks, where adversaries poison safety alignment data to embed hidden triggers that bypass safety mechanisms. Existing defenses often require comprehensive attack information or multiple triggered examples, making them impractical wh...