PT-2026-41213

Name of the Vulnerable Software and Affected Versions Flowise versions prior to 3.1.2 Description A mass assignment issue exists in the DatasetRow create and update processes. The application uses Object.assign to copy the request body into the DatasetRow entity without an explicit field allowlis...

WARD: Adversarially Robust Defense of Web Agents against Prompt Injections

Web agents can autonomously complete online tasks by interacting with websites, but their exposure to open web environments makes them vulnerable to prompt injection attacks embedded in HTML content or visual interfaces. Existing guard models still suffer from limited generalization to unseen...

PT-2026-41212

Name of the Vulnerable Software and Affected Versions Flowise versions prior to 3.1.2 Description A mass assignment issue exists in the dataset create and update processes. The application uses Object.assign to copy the request body into a Dataset entity without an explicit field allowlist,...

Characterizing AI-Assisted Bot Traffic in Darknet Data: Implications for ICS and IIoT Security

The rise of automated scanning tools and AI assisted reconnaissance agents has significantly altered internet background traffic patterns, threatening the baseline assumptions underlying intrusion detection systems IDS deployed in critical infrastructure networks. This paper characterizes the...

Still Camouflage, Moving Illusion: View-Induced Trajectory Manipulation in Autonomous Driving

Existing physical adversarial attacks on vision-based autonomous driving induce time-evolving perception errors, including biased object tracking or trajectory prediction, through i sophisticated physical patch inducing detection box drift when entering the view distance, or ii dynamically changi...

VulTriage: Triple-Path Context Augmentation for LLM-Based Vulnerability Detection

Automated vulnerability detection is a fundamental task in software security, yet existing learning-based methods still struggle to capture the structural dependencies, domain-specific vulnerability knowledge, and complex program semantics required for accurate detection. Recent Large Language...

CVE-2026-31237

The Ludwig framework thru 0.10.4 is vulnerable to insecure deserialization CWE-502 through its predict method. When a user provides a dataset file path to the predict method, the framework automatically determines the file format. If the file is a pickle .pkl file, it is loaded using...

The Art of the Jailbreak: Formulating Jailbreak Attacks for LLM Security beyond Binary Scoring

Jailbreak attacks -- adversarial prompts that bypass LLM alignment through purely linguistic manipulation -- pose a growing operational security threat, yet the field lacks large-scale, reproducible infrastructure for generating, categorizing, and evaluating them systematically. This paper...

Enhancing Adversarial Robustness in Network Intrusion Detection: A Layer-Wise Adaptive Regularization Approach

The new wave of adversarial attacks that utilize gradient-related vulnerabilities in neural network-based classifiers makes Network Intrusion Detection Systems more open to such threats. Although state-of-the-art adversarial training methods have shown promising results in producing more robust...

Security Bulletin: IBM Watson Discovery Cartridge affected by vulnerability in keras-3.13.1-py3-none-any.whl

Summary IBM Watson Discovery Cartridge affected by vulnerability in keras-3.13.1-py3-none-any.whl Vulnerability Details CVEID:CVE-2026-1669 DESCRIPTION: Arbitrary file read in the model loading mechanism HDF5 integration in Keras versions 3.0.0 through 3.13.1 on all supported platforms allows a...

LCC-LLM: Leveraging Code-Centric Large Language Models for Malware Attribution

LLMs are increasingly explored for malware analysis; however, current LLM-based malware attribution remains limited by unsupported indicators and insufficient code-level grounding for identifying malicious and vulnerable code segments. To address these limitations, this research introduces LCC-LL...

Benchmarking Large Language Models for IoC Recovery under Adversarial Code Obfuscation and Encryption

Software obfuscation and encryption present persistent challenges for program comprehension and security analysis, particularly when adversaries conceal Indicators of Compromise IoCs such as IP addresses within source code. While Large Language Models LLMs have recently demonstrated remarkable...

TUANDROMD-X: Advanced Entropy and Visual Analytics Dataset for Enhanced Malware Detection and Classification

Malware and malware-based attacks are becoming more prevalent and complex. Attackers regularly come up with new techniques that have the ability to evade conventional and signature-based malware defense. In order to address such threats, there is an increasing demand for advanced and better defen...

Beyond the Wrapper: Identifying Artifact Reliance in Static Malware Classifiers Using TRUSTEE

Modern cybersecurity relies heavily on static machine-learning-based malware classifiers. However, transformations such as packing and other non-semantic modifications applied to executable files limit their reliability. Malware classifiers often learn these unnecessary artifacts rather than the...

DecodingTrust-Agent Platform (DTap): A Controllable and Interactive Red-Teaming Platform for AI Agents

AI agents are increasingly deployed across diverse domains to automate complex workflows through long-horizon and high-stakes action executions. Due to their high capability and flexibility, such agents raise significant security and safety concerns. A growing number of real-world incidents have...

CVE-2026-7681

A security vulnerability has been detected in jsbroks COCO Annotator up to 0.11.1. Affected by this vulnerability is an unknown functionality of the file backend/webserver/api/datasets.py of the component Dataset API. The manipulation of the argument DatasetId leads to authorization bypass. The...

Tailored Prompts, Targeted Protection: Vulnerability-Specific LLM Analysis for Smart Contracts

Smart contracts on blockchains are prone to diverse security vulnerabilities that can lead to significant financial losses due to their immutable nature. Existing detection approaches often lack flexibility across vulnerability types and rely heavily on manually crafted expert rules. In this pape...

HackerSignal: A Large-Scale Multi-Source Dataset Linking Hacker Community Discourse to the CVE Vulnerability Lifecycle

We introduce HackerSignal, a benchmark for temporal out-of-distribution cyber threat intelligence CTI and cross-source CVE linkage. HackerSignal aggregates 7.45 million exact-deduplicated documents from 64 public forum/source identifiers spanning eight source layers and a 36-year window 1990-2026...

A Validated Prompt Bank for Malicious Code Generation: Separating Executable Weapons from Security Knowledge in 1,554 Consensus-Labeled Prompts

Existing benchmarks of language-model refusal on malicious-coding tasks routinely conflate requests for executable malicious software with requests for harmful security knowledge. This conflation matters because the two request types plausibly trigger distinct refusal pathways in safety-aligned...

Evaluating Tabular Representation Learning for Network Intrusion Detection

Classic Network Intrusion Detection Systems NIDS often rely on manual feature engineering to extract meaningful patterns from network traffic data. However, this approach requires domain expertise and runs counter to the widely adopted principle of modern machine learning and neural networks: tha...