AI Security Research Should Better Incentivize Defense Research

This work examines an imbalance in artificial intelligence AI security research: the field tends to produce more work on attacking AI systems than on defending them. Drawing on related academic papers, we find biased attack-to-defense ratios across subfields, including federated learning, speech...

An Empirical Evaluation of LLM-Generated Code Security across Prompting Methods

The growing use of Large Language Models LLMs for automated code generation has enhanced software development efficiency, but often at the cost of security. Generated code frequently overlooks critical concerns, leaving it vulnerable to issues such as weak encryption and improper input validation...

Security of LLM-Generated Code: A Comparative Analysis

The majority of software developers use or are planning to use Artificial Intelligence AI tools in their development processes. Their top reasons include improving productivity and faster learning. In fact, Large Language Model LLM-generated code is currently in production, including in major tec...

Pretraining Data Exposure in Large Language Models: A Survey of Membership Inference, Data Contamination, and Security Implications

Large Language Models LLMs have become the predominant paradigm in NLP, advancing both research and industry. As model sizes and pretraining data grow, concerns about Pretraining Data Exposure PDE increase due to the scale and opacity of training datasets. PDE refers to determining whether specif...

HIDBench: Benchmarking Large Language Models for Host-Based Intrusion Detection

Recent benchmark efforts have advanced the evaluation of large language models LLMs in cybersecurity, including tasks such as penetration testing and vulnerability identification. However, a critical cybersecurity task, namely intrusion detection from system logs, remains unexplored. In this work...

Kimsuky targets organizations with PebbleDash-based tools

Over the past few months, we have conducted an in-depth analysis of specific activity clusters of Kimsuky aka APT43, Ruby Sleet, Black Banshee, Sparkling Pisces, Velvet Chollima, and Springtail, a prolific Korean-speaking threat actor. Our research revealed notable tactical shifts throughout...

Detecting Privilege Escalation in Polyglot Microservices Via Agentic Program Analysis

Microservices are widely adopted in modern cloud systems due to their scalability and fault tolerance. However, microservice architectures introduce significant complexity in privilege and permission control, creating risks of privilege escalation where attackers can gain unauthorized access to...

UGen: An Agentic Framework for Generating Microarchitectural Attack PoCs

Microarchitectural attacks continue to evolve, uncovering new exploitation vectors in modern processors. From a defensive perspective, assessing a system's susceptibility to such attacks remains challenging. Developing functional attack implementations is labor-intensive, requires deep...

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...

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...

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...

LLMs and Text-in-Text Steganography

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

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...

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...

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...

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...

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...

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...