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...

hermes-agent v2026.8.18

Hermes Agent ☤ Hermes Agent | Hermes Desktop The self-improving AI agent built byNous Research. It's the only agent with a built-in learning loop — it creates skills from experience, improves them during use, nudges itself to persist knowledge, searches its own past conversations, and builds a...

REPLICANT: Learning Policies for Evading and Hardening Malware Detectors

To determine the real-world effectiveness of machine learning based malware detection, it is vital to evaluate its robustness against highly capable adversaries. However, state-of-the-art attacks do not effectively model realistic adversaries, as they often assume access to privileged information...

Enhancing Web Application Firewalls with Machine Learning for SQL Injection Detection

Detecting SQL Injection SQLi attacks ranks among the most critical challenges in web application security. This research conducted a systematic literature review to identify the research gaps in this domain and responsively designed and optimised a DistilBERT-Stacked Ensemble pipeline to improve...

ContextLeak: Exfiltrating LLM Agent Context Via Malicious Tools

Exfiltrating an LLM agent's runtime context -- such as the user prompt, execution trajectory, and tool list -- poses severe security and privacy risks to users. Such attacks can be carried out via malicious tools and typically require three conditions: 1 the agent selects the malicious tool for...

Low-ASR Backdoors: Exploiting Attack Success Rate Reduction and Attacker-Defender Asymmetry

Backdoor attacks are among the most effective and stealthy attacks in deep learning. Existing attacks and defenses are largely designed and evaluated under the assumption that successful backdoors exhibit high Attack Success Rates ASRs. In this paper, we show that this assumption creates a...

CavalryHive

CavalryHive Autonomous web-security assessment toolkit for...

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...

cybershield-ai

AI-Powered Network Intrusion & Phishing Detection System An e...

Security-Aware Pinching-Antenna Systems (PASS): Physical-Layer Security Transmission

This paper investigates heterogeneous secure multi-user transmission in pinching-antenna systems PASS, where dynamically adjustable pinching antennas reshape both guided-wave and free-space propagation to improve communication and confidentiality performance. Unlike conventional physical-layer...

Adapter-Based Few-Shot Continual Learning for Malicious Packet Recognition

The continual evolution of malware variants necessitates detection systems that can adapt to new threats without retraining from scratch. However, continually updating models on new data often leads to catastrophic forgetting, where previously learned knowledge is overwritten. While continual...

RAD: Rule-Augmented Relational Anomaly Detection

Anomaly detection is often applied to data stored in relational databases, yet most existing methods require flattening multiple tables into a single feature matrix. This flattening can obscure entity identity, schema structure, and multi-hop dependencies, limiting the detection of anomalies that...

Mitigating Explanation Leakage in Financial Fraud Detection Systems

Financial fraud detection relies heavily on centralized machine learning models. This creates serious data privacy risks. Federated Learning FL decentralizes data processing, but financial regulations still require models to be transparent. This means using Explainable AI XAI tools such as...

xsslab

XSS Educational Learning Lab 🛡️ An interactive, educational w...

On Predicting Vulnerability Severity Using In-Context Learning: An Industrial Case Study

Modern software systems require earlier and more scalable vulnerability severity assessment to reduce exposure to high-impact security flaws. Security analysts typically assign CVSS scores, but this manual triage does not scale with the growth of disclosed vulnerabilities and often depends on clo...

Kibana 8.x < 8.19.20 / 9.x < 9.4.5 Multiple Vulnerabilities (ESA-2026-92 / ESA-2026-98 / ESA-2026-100 / ESA-2026-104 / ESA-2026-105 / ESA-2026-106 / ESA-2026-110)

The version of Kibana installed on the remote host is 8.x prior to 8.19.20, or 9.x prior to 9.4.5. It is, therefore, affected by multiple vulnerabilities as referenced in the ESA-2026-92, ESA-2026-98, ESA-2026-100, ESA-2026-104, ESA-2026-105, ESA-2026-106 and ESA-2026-110 advisories. - Missing...

poc-inteligencia-tributaria-palmas

PoC — Inteligência Tributária de Palmas-TO !CIhttps://git...

TGL-APT: Temporal Graph Learning with Graph Distillation for Efficient APT Investigation

Advanced Persistent Threat APT attacks pose a critical challenge to modern systems, as their stealthy, multi-stage nature renders conventional detection methods ineffective. While provenance graphs provide rich behavioral context for attack investigation, attack-relevant evidence is often sparse...

OpenAI Pauses Frontier RL Training as It Tightens Defenses Against Unsafe AI Behavior

OpenAI on Tuesday revealed that it paused reinforcement learning RL training for its latest artificial intelligence AI models for two weeks while it shored up additional defenses and increased the scope of its monitoring to avert another Hugging Face-like incident. "As models become more capable,...

BIT-KIBANA-2026-72675 Missing Authorization in Kibana Machine Learning Leading to Cross-Space Information Disclosure and Unauthorized Data Modification

Missing Authorization CWE-862 in Kibana can lead to cross-space information disclosure and unauthorized data modification via Privilege Abuse CAPEC-122. Kibana Machine Learning carries out its Elasticsearch operations with elevated internal permissions and relies on a per-request space filter to...