AI-Generated PowerShell Malware: An Experimental Framework and Dataset

Generative AI has emerged as a significant cybersecurity threat, with several recent attack campaigns leveraging LLMs to generate code for malicious purposes via scripting languages such as PowerShell. Consequently, for cybersecurity analysts, it is imperative to investigate the offensive...

Benchmark AUC Is Not Deployable Reliability: A Cross-Dataset Audit of Off-The-Shelf Features for Surveillance Video Anomaly Detection

Automated "suspicious behavior" flagging is a headline promise of AI surveillance, and the field reports high frame-level ROC-AUC on standard video anomaly detection benchmarks. Those numbers are measured by training and testing on the same camera and scene. We audit what happens when that...

vuln-corpus

Exploitarium Vulnerability Corpus Structured vulnerabilit...

Missing Authentication For Critical Function

Backpropagate is vulnerable to Missing Authentication for Critical Function. The vulnerability is due to the Reflex web UI failing to enforce the --auth authentication mechanism despite indicating it is enabled, which allows an attacker who can access the exposed UI port to perform unauthorized...

Backpropagate: backprop ui --auth and backprop ui --share do not enforce authentication

Summary In backpropagate = 1.1.0, the optional Reflex web UI pip install backpropagateui, launched via backprop ui exposes a training control plane: dataset upload, model load, training start/stop, multi-run orchestration, GGUF export, and HuggingFace Hub push. The CLI accepts two operator-facing...

GHSA-F65R-H4G3-3H9H Backpropagate: backprop ui --auth and backprop ui --share do not enforce authentication

Summary In backpropagate = 1.1.0, the optional Reflex web UI pip install backpropagateui, launched via backprop ui exposes a training control plane: dataset upload, model load, training start/stop, multi-run orchestration, GGUF export, and HuggingFace Hub push. The CLI accepts two operator-facing...

CVE-2026-56445

The CVE-2026-56445 issue affects the qrscp application’s C-STORE handler. It directly uses an attacker-supplied DICOM dataset instance in os.path.join() without sanitization, enabling writes to arbitrary file paths on the system. This is a path traversal vulnerability in the file-write path, with...

Poster: Exploring the Limits of Audio-Based Detection of Turkish Phone Call Scams

Scam phone calls exploit vulnerable communities worldwide, yet research on detection has focused almost exclusively on English and other high-resource languages. In low-resource settings such as Turkish, detection is especially difficult, as annotated data is scarce and technological defenses...

Understanding the Stealthy BGP Hijacking Risk in the ROV Era

The partial deployment of Route Origin Validation ROV poses an unexpected security threat known as stealthy BGP hijacking, i.e., a particularly elusive form of BGP hijacking where malicious routes divert traffic without reaching and thus alerting the victims. This risk remains largely unexplored,...

Detecting Malicious Agent Skills in the Wild Using Attention

LLM agents increasingly load skills, file-based packages of natural-language instructions written by third parties and distributed through marketplaces, that execute with the user's privileges. A single malicious skill can exfiltrate data, hijack the agent, or persist as a supply-chain foothold,...

A Hybrid Intrusion Detection System for Electric Vehicle Charging Infrastructure

The integration of Electric Vehicle Charging Stations EVCSs into the smart grid necessitates sophisticated digital infrastructure for their management and coordination, which expands the attack surface and makes both the power grid and EVCSs vulnerable to cyberattacks. This research addresses...

LLM Agent Safety, Multi-Turn Red-Teaming, Jailbreak Benchmarks, Adversarial Robustness, Safety-Critical Systems

Large language model LLM agents are increasingly proposed as supervisory components for safety-critical systems, yet their robustness under sustained, adaptive adversarial pressure remains poorly characterized. We present NRT-Bench, a benchmark for multi-turn red-teaming of LLM agents acting as...

CVE-2026-48797

Backpropagate is a Python library for fine-tuning LLMs on a single GPU. In versions 1.1.0 and 1.1.1, the Reflex web UI exposes a training control plane without authentication, allowing dataset upload, model load, training control, multi-run orchestration, GGUF export, and HuggingFace Hub push. Th...

CVE-2026-48797 Backpropagate: backprop ui --auth and backprop ui --share do not enforce authentication

Backpropagate is a Python library for fine-tuning large language models on a single GPU. In versions 1.1.0 and 1.1.1, the optional Reflex web UI exposes a training control plane without authentication: dataset upload, model load, training start/stop, multi-run orchestration, GGUF export, and...

ARES: A Platform for Adaptive Role-Based Evaluation of Social Engineering Risks in Human--AI Games

This work introduces ARES, a platform and open pilot dataset for auditing adaptive social engineering risks in LLM-mediated social decision-making through controlled social games. ARES supports human--human, human--AI, and AI--AI settings, combining configurable game templates, role-conditioned L...

ARVO: Atlas of Reproducible Vulnerabilities for Open-Source Software

Achieving reproducibility, quantity, and diversity in vulnerability datasets has long been viewed as an inherent three-way trade-off, where improving one dimension often comes at the cost of the others. In practice, reproducibility has been the dimension most often neglected. This has limited wha...

MASCOT-Android: A Curated Dataset and Automated Collection Pipeline for Android Malware Source Code Specimens

Compared with binaries and decompiled code, malware source code more directly reflects the attackers' original intent. However, the scarcity of source code and the high cost of manual review make such datasets difficult to build and maintain. We propose MASCOT-Android, a curated dataset of Androi...

Evaluating LLMs for Obfuscation Detection and Classification in Android Apps

Android applications apps developers increasingly rely on code obfuscation techniques to hinder reverse engineering and protect intellectual property. However, obfuscation also reduces the effectiveness of static analysis and vulnerability detection tools, creating challenges for Android security...

Cross-Site Scripting (XSS)

CKAN is vulnerable to Cross-Site Scripting XSS. The vulnerability is due to insufficient sanitization of user-supplied input in the helpers.markdownextract function before it is wrapped in an HTML literal element, which allows an attacker to inject and execute malicious scripts on dataset,...

CVE-2026-42558

Xibo is an open source digital signage platform with a web content management system and Windows display player software. Prior to 4.4.2, a vulnerability chain consisting of Stored XSS and Iframe Sandbox escape in the Xibo CMS allows users with DataSet permissions to use the Data Connector...