AICrypto: a Comprehensive Benchmark for Evaluating Cryptography Capabilities of Large Language Models

Whitepaper called AICrypto: A Comprehensive Benchmark For Evaluating Cryptography Capabilities Of Large Language Models...

When Developer Aid Becomes Security Debt: a Systematic Analysis of Insecure Behaviors in LLM Coding Agents

LLM-based coding agents are rapidly being deployed in software development, yet their security implications remain poorly understood. These agents, while capable of accelerating software development, may inadvertently introduce insecure practices. We conducted the first systematic security...

ARPaCCino: an Agentic-RAG for Policy As Code Compliance

Policy as Code PaC is a paradigm that encodes security and compliance policies into machine-readable formats, enabling automated enforcement in Infrastructure as Code IaC environments. However, its adoption is hindered by the complexity of policy languages and the risk of misconfigurations. In th...

The Prompt as a Rulebook - Guiding LLM Agents Beyond Basic Instructions

...

Can Large Language Models Improve Phishing Defense? A Large-Scale Controlled Experiment on Warning Dialogue Explanations

Phishing has become a prominent risk in modern cybersecurity, often used to bypass technological defences by exploiting predictable human behaviour. Warning dialogues are a standard mitigation measure, but the lack of explanatory clarity and static content limits their effectiveness. In this pape...

Phishing Detection in the Gen-AI Era: Quantized LLMs Vs Classical Models

Phishing attacks are becoming increasingly sophisticated, underscoring the need for detection systems that strike a balance between high accuracy and computational efficiency. This paper presents a comparative evaluation of traditional Machine Learning ML, Deep Learning DL, and quantized...

Securing the Frontier - Navigating Security in LLM-Integrated Systems

In the previous parts of this series, we've explored the exciting new ways Large Language Models LLMs can integrate with APIs and act as intelligent As we integrate LLMs deeper into our applications, the attack surface naturally expands...

Bridging AI and Software Security: a Comparative Vulnerability Assessment of LLM Agent Deployment Paradigms

Large Language Model LLM agents face security vulnerabilities spanning AI-specific and traditional software domains, yet current research addresses these separately. This study bridges this gap through comparative evaluation of Function Calling architecture and Model Context Protocol MCP deployme...

LIFT: Automating Symbolic Execution Optimization with Large Language Models for AI Networks

Dynamic Symbolic Execution DSE is a key technique in program analysis, widely used in software testing, vulnerability discovery, and formal verification. In distributed AI systems, DSE plays a crucial role in identifying hard-to-detect bugs, especially those arising from complex network...

The Landscape of Memorization in LLMs: Mechanisms, Measurement, and Mitigation

Large Language Models LLMs have demonstrated remarkable capabilities across a wide range of tasks, yet they also exhibit memorization of their training data. This phenomenon raises critical questions about model behavior, privacy risks, and the boundary between learning and memorization. Addressi...

Large Language Models for Network Intrusion Detection Systems: Foundations, Implementations, and Future Directions

Large Language Models LLMs have revolutionized various fields with their exceptional capabilities in understanding, processing, and generating human-like text. This paper investigates the potential of LLMs in advancing Network Intrusion Detection Systems NIDS, analyzing current challenges,...

Rethinking and Exploring String-Based Malware Family Classification in the Era of LLMs and RAG

Malware Family Classification MFC aims to identify the fine-grained family e.g., GuLoader or BitRAT to which a potential malware sample belongs, in contrast to malware detection or sample classification that predicts only an Yes/No. Accurate family identification can greatly facilitate automated...

Can Large Language Models Automate the Refinement of Cellular Network Specifications?

Cellular networks serve billions of users globally, yet concerns about reliability and security persist due to weaknesses in 3GPP standards. However, traditional analysis methods, including manual inspection and automated tools, struggle with increasingly expanding cellular network specifications...

The New Toolkit: LLMs, Prompts, and Basic Tool Interaction

...

The Rise of Agentic AI: Uncovering Security Risks in AI Web Agents

In our first post, we introduced the world of AI web agents - defining what they are, outlining their core capabilities, and surveying the leading frameworks that make them possible. Now, we’re shifting gears to look at the other side of the coin: the vulnerabilities and attack surfaces that aris...

Jailbroken AIs are helping cybercriminals to hone their craft

Cybercriminals are bypassing the guardrails that are supposed to keep AI models from carrying out criminal activities, according to researchers. We've seen the misuse of AI models by cybercriminals growing rapidly over the past several years, shaping a new era of digital threats. Early on,...

The Paradigm Shift: From Traditional APIs to Language-Driven Integration

Large language models LLMs are changing the game, offering a new way for systems to interact based on understanding language, not just strict formats...

On the Feasibility of Poisoning Text-To-Image AI Models Via Adversarial Mislabeling

Today's text-to-image generative models are trained on millions of images sourced from the Internet, each paired with a detailed caption produced by Vision-Language Models VLMs. This part of the training pipeline is critical for supplying the models with large volumes of high-quality image-captio...

Cybercriminal abuse of large language models

Cybercriminals are continuing to explore artificial intelligence AI technologies such as large language models LLMs to aid in their criminal hacking activities. Some cybercriminals have resorted to using uncensored LLMs or even custom-built criminal LLMs for illicit purposes. Advertised features ...

JsDeObsBench: Measuring and Benchmarking LLMs for JavaScript Deobfuscation

Deobfuscating JavaScript JS code poses a significant challenge in web security, particularly as obfuscation techniques are frequently used to conceal malicious activities within scripts. While Large Language Models LLMs have recently shown promise in automating the deobfuscation process,...