STARE: Step-Wise Temporal Alignment and Red-Teaming Engine for Multi-Modal Toxicity Attack

Red-teaming Vision-Language Models is essential for identifying vulnerabilities where adversarial image-text inputs trigger toxic outputs. Existing approaches treat image generation as a black box, returning only terminal toxicity scores and leaving open the question of when and how toxic semanti...

Trident: Improving Malware Detection with LLMs and Behavioral Features

Traditionally, machine learning methods for PE malware detection have relied on static features like byte histograms, string information, and PE header contents. One barrier to incorporating dynamic analysis features has been the semi-structured nature of sandbox behavior reports. We show that,...

Towards Agentic Investigation of Security Alerts

Security analysts are overwhelmed by the volume of alerts and the low context provided by many detection systems. Early-stage investigations typically require manual correlation across multiple log sources, a task that is usually time-consuming. In this paper, we present an experimental, agentic...

From CRUD to Autonomous Agents: Formal Validation and Zero-Trust Security for Semantic Gateways in AI-Native Enterprise Systems

Enterprise software engineering is shifting away from deterministic CRUD/REST architectures toward AI-native systems where large language models act as cognitive orchestrators. This transition introduces a critical security tension: probabilistic LLMs weaken classical mechanisms for validation,...

Logic-to-Code Execution via Indirect Prompt Injection

This document explores a critical architectural vulnerability in Large Language Model LLM implementations, specifically within Command Line Interface CLI tools and automated agentic workflows. The research demonstrates how the absence of separation between the control plane instructions and the...

Symbolic Execution Meets Multi-LLM Orchestration: Detecting Memory Vulnerabilities in Incomplete Rust CVE Snippets

This paper presents a system combining symbolic execution KLEE with a 4-agent multi-LLM architecture for detecting memory vulnerabilities in Rust unsafe code. A central challenge we address is the incomplete-code problem: CVE database entries provide only isolated code snippets that lack struct...

Evaluation of Prompt Injection Defenses in Large Language Models

LLM-powered applications routinely embed secrets in system prompts, yet models can be tricked into revealing them. We built an adaptive attacker that evolves its strategies over hundreds of rounds and tested it against nine defense configurations across more than 20,000 attacks. Every defense tha...

EUVD-2026-25333

OpenClaw before 2026.3.28 contains an agentic consent bypass vulnerability allowing LLM agents to silently disable execution approval via config.patch parameter. Remote attackers can exploit this to bypass security controls and execute unauthorized operations without user consent...

Flowise Information Disclosure Vulnerability

Flowise is a FlowiseAI open source tool for easily building LLM applications. Flowise suffers from an information disclosure vulnerability caused by a flaw in the /api/v1/public-chatflows/:id endpoint that can be exploited by an attacker to obtain sensitive information...

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...

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...

llm-security-lab

LLM Security Lab Laboratoire de sécurité pour application...

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...

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...

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...

RAVEN: Retrieval-Augmented Vulnerability Exploration Network for Memory Corruption Analysis in User Code and Binary Programs

Large Language Models LLMs have demonstrated remarkable capabilities across various cybersecurity tasks, including vulnerability classification, detection, and patching. However, their potential in automated vulnerability report documentation and analysis remains underexplored. We present RAVEN...

GuardPhish: Securing Open-Source LLMs from Phishing Abuse

The rapid adoption of open-source Large Language Models LLMs in offline and enterprise environments has introduced a largely unexamined security risk like susceptibility to adversarial phishing prompts under static safety configurations. In this work, we systematically investigate this...