CVE-2026-44223

vLLM contains a vulnerability (CVE-2026-44223) where the extract_hidden_states speculative decoding pathway can crash the EngineCore process if any request uses penalty parameters (repetition_penalty, frequency_penalty, or presence_penalty). The issue arises from an incorrect tensor shape after t...

When LLMs Team Up: A Coordinated Attack Framework for Automated Cyber Intrusions

Automated intrusion-style workflows require LLM agents to reason over partial observations, tool outputs, and executable artifacts under bounded budgets. A single LLM instance often compresses evidence extraction, planning, execution, and validation into one context, which increases the risk of...

This Week in Spring - May 12th, 2026

Hi, Spring fans! As I write this I am in Miami, FL at the CodeRemix.ai show, focused on the wide and wonderful world of OpenRewrite and Moderne. I've got a talk to give so let's dive right into it! a quick note about the upcoming release train dates in last week's installment of A Bootiful Podcas...

CTFusion: A CTF-Based Benchmark for LLM Agent Evaluation

Recent advances in Large Language Models LLMs have enabled agentic systems for complex, multi-step tasks; cybersecurity is emerging as a prominent application. To evaluate such agents, researchers widely adopt Capture The Flag CTF benchmarks. However, current CTF benchmarks reuse existing...

LLMs and Text-in-Text Steganography

Turns out that LLMs are really good at hiding text messages in other text messages...

LLMs for Secure Hardware Design and Related Problems: Opportunities and Challenges

The integration of Large Language Models LLMs into Electronic Design Automation EDA and hardware security is rapidly reshaping the semiconductor industry. While LLMs offer unprecedented capabilities in generating Register Transfer Level RTL code, automating testbenches, and bridging the semantic...

Guaranteed Jailbreaking Defense Via Disrupt-And-Rectify Smoothing

This paper proposes a guaranteed defense method for large language models LLMs to safeguard against jailbreaking attacks. Drawing inspiration from the denoised-smoothing approach in the adversarial defense domain, we propose a novel smoothing-based defense method, termed Disrupt-and-Rectify...

Adversarial SQL Injection Generation with LLM-Based Architectures

SQL injection SQLi attacks are still one of the serious attacks ranked in the Open Worldwide Application Security Project OWASP Top 10 threats. Today, with advances in Artificial Intelligence AI, especially in Large Language Models LLMs, an opportunity has been created for automating adversarial...

Mythos

Mythos Autonomous cybersecurity agent that connects to multip...

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...

AFL-ICP: Enhancing Industrial Control Protocol Reliability Via Specification-Guided Fuzzing

Industrial Control Protocols ICPs are critical to the reliability and stability of industrial infrastructure, yet their security is fundamentally compromised by a specification-blindness bottleneck. Modern fuzzers, constrained by observation-driven inference, struggle to penetrate deep protocol...

Information Theoretic Adversarial Training of Large Language Models

Large language models LLMs remain vulnerable to adversarial prompting despite advances in alignment and safety, often exhibiting harmful behaviors under novel attack strategies. While adversarial training can improve robustness, existing approaches are computationally expensive and difficult to...

SOCpilot: Verifying Policy Compliance for LLM-Assisted Incident Response

Security operations centers SOCs are beginning to use large language models LLMs as copilots to draft incident-response plans. These plans may include actions that are valid per the catalog but still violate mandatory steps, required ordering, or approval gates before analyst review. SOCpilot mak...

Evaluating the Reliability of Multiple Large Language Models in Risk Assessment: A CIS Controls Based Approach

Proper implementation of technical and administrative controls reinforces an organization's cybersecurity posture and business resilience, reduces risks, and enhances governance, ultimately elevating business maturity. The dynamics of the technological landscape and emerging threats negatively...

Automation-Exploit-Legacy

Automation-Exploit Legacy Prototype This repository contain...

This Week in Spring - May 5th, 2026

Hi, Spring fans! Welcome to another installment of This Week in Spring! It's May 5th, 2026, and I'm in Mainz, Germany, for the legendary JAX conference! It's been infinitely far too long since I've been at this amazing show, and I'm oh-so happy to be back here! Tonight, after my two talks here, I...

Eval Injection

Overview pptagent is an An Agentic Framework for Reflective PowerPoint Generation Affected versions of this package are vulnerable to Eval Injection via the eval function when processing code generated by large language models with built-in functions available in the execution scope. An attacker...

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...