Domain-Specific Security Applications
Research applying LLMs to security challenges in specific domains like code analysis, finance, and threat intelligence
Domain-Specific Security Applications
Research on Large Language Models in Domain-Specific Security Applications
PoliGraph: Making Sense of Privacy Policies
Using Knowledge Graphs to Detect Policy Contradictions
BotArtist: Detecting Twitter Bots
A semi-automatic approach to fight disinformation and manipulation
Harnessing ChatGPT to Combat Phishing Attacks
Using LLMs as a powerful defense against cybersecurity threats
Security Risks in AI-Generated Code
Empirical analysis of security vulnerabilities in GitHub Copilot code
Privacy Vulnerabilities in Federated Learning
How attackers can steal sensitive data from language models without accessing raw data
Nova: AI-Powered Assembly Code Analysis
Enhancing security through specialized language models for binary code
LLMs Revolutionize Kernel Security
Enhancing fuzzing with AI to find critical OS vulnerabilities
Automating Threat Intelligence
Blending global and local cyber knowledge for personalized security
Leveraging Language Models for Credit Risk
Using BERT to extract risk signals from P2P loan descriptions
Fortifying Recommender Systems
Using LLMs to Defend Against Poisoning Attacks
Smart Contract Security Through Improved Summarization
Leveraging LLMs with Control Flow Analysis for Safer Smart Contracts
Intelligent Log Parsing with Lemur
Enhancing System Monitoring through Advanced AI
Enhancing Digital Forensics with LLMs
Exploring AI solutions for overwhelmed forensic labs
Securing LLM Agents
Introducing IsolateGPT: Execution Isolation for LLM App Ecosystems
Securing Blockchain with AI
Leveraging Large Language Models for Enhanced Blockchain Security
Security Gaps in Rust's Foreign Function Interface
Detecting undefined behaviors across language boundaries
Backdoor Threats in Code LLMs
Converting AI Backdoors to Traditional Malware
Harnessing LLMs for Protocol Security
Using AI to detect vulnerabilities by inferring state machines
IRIS: AI-Powered Security Shield
Combining LLMs with Static Analysis for Better Vulnerability Detection
HoneyGPT: Revolutionizing Cybersecurity Deception
Using LLMs to create more adaptive, interactive honeypots
Advancing Log Parsing with AI
Using LLMs to self-learn and self-correct for better security insights
Benchmarking LLMs for Cybersecurity
A New Framework for Testing AI in Offensive Security
FlexLog: Effective Anomaly Detection in Unstable Logs
Combining Large Language Models with ML for Data-Efficient Cybersecurity
LLM-Powered Network Health Management
Revolutionizing network anomaly detection through semantic understanding
Package Hallucinations: A New Security Threat
How LLMs create software supply chain vulnerabilities
AI-Generated Phishing: A New Security Threat
Comparing AI vs Human-Authored Spear Phishing SMS Attacks
Securing LLM Integration
Uncovering critical flaws in how developers implement LLMs in software
Securing AI-Generated Code
How Prompting Techniques Impact Security Vulnerabilities
Aurora: AI-Powered Cyberattack Emulation
Automating Attack Planning with LLMs and Classical Planning
Open-FinLLMs: Revolutionizing Financial Intelligence
The first open-source multimodal LLMs for comprehensive financial applications
APPATCH: AI-Powered Vulnerability Patching
Automating software security fixes with adaptive prompting of LLMs
Detecting Vulnerabilities Without Labeled Data
LLM-based anomaly detection outperforms direct LLM vulnerability prediction
Enhancing Log Analysis with LLM Knowledge
Knowledge-driven approach for efficient log understanding
LLMs as Security Sentinels
Revolutionizing Anomaly & Out-of-Distribution Detection
LLMs for Security Log Analysis
Revolutionizing Cyber Security with Template Detection
News Ripples Through Supply Chain Networks
How positive and negative news impacts stock prices across connected firms
MarS: Simulating Financial Markets with AI
Using Large Language Models to Create Realistic Market Environments
Combating Financial Misinformation with AI
How Large Language Models Can Detect Financial Falsehoods
Securing the Supply Chain
Automatic Verification of Vulnerabilities in Third-Party Dependencies
Navigating the Safety Frontier of AI in Healthcare
Balancing innovation with responsible implementation of LLMs in medicine
DomainLynx: AI-Powered Cybersecurity
Enhancing Domain Squatting Detection with Large Language Models
Securing POI Recommendation Systems
A comprehensive analysis of security threats and safeguards in location-based recommendations
ChatGPT Meets Malware Detection
Leveraging LLMs to Enhance Android Security
Unlocking Time Series Anomaly Detection with LLMs
Exploring LLMs' untapped potential beyond forecasting
TEOChat: Temporal Vision for Earth Observation
First LLM assistant that analyzes time-series satellite imagery
Smart Motion Prediction for Autonomous Vehicles
Advancing Self-Supervised Learning for Safer Autonomous Driving
Ensuring Safe AI Agents for Mobile Interfaces
A framework for evaluating the impact and risks of AI actions on mobile UIs
Scaling Up Targeted AI Attacks
A Simple Transformation Technique for Attacking Black-Box Models
AI-Powered Smart Contract Security
Automating Blockchain Security Audits with Fine-Tuned LLMs
Safety Blind Spots in AI Lab Assistants
Benchmarking LLMs on Critical Laboratory Safety Risks
Intelligent Safety Filters for Robot Manipulation
Teaching robots 'common sense' safety constraints through semantics
Improving Smart Contract Transparency
AI-Powered Decompiler for Blockchain Security
AI-Powered Formal Verification
Enabling LLMs to automatically generate security proofs for Rust code
AI-Powered Ethical Hacking
Benchmarking LLMs for Automated Penetration Testing
Next-Gen Surveillance with Zero-Shot Learning
Leveraging LVLMs for Action Recognition Without Training Data
Supercharging Anomaly Detection with LLMs
Using language models to detect system issues in log data
Unified Vision-Language for Autonomous Driving
Aligning BEV Perception with Natural Language Understanding
Securing Code Generation in LLMs
Proactive security alignment to prevent vulnerabilities in AI-generated code
Cleaning Up Vulnerability Detection in Code
Using LLMs to spot real vulnerabilities in software commits
Spotting the Unusual: AI-Powered Anomaly Detection
A breakthrough benchmark for text-based detection of abnormal pedestrian behaviors
Bridging the AI Security Gap
Advancing Autonomous Penetration Testing with AI Generalization Techniques
Trusted AI Through Neural Interactive Proofs
A Framework for Secure Collaboration Between Trusted and Untrusted AI Systems
Safeguarding AI Agents in the Physical World
A new benchmark for evaluating the safety of embodied AI agents
Automating Formal Verification with AI
How Rango uses LLMs to streamline software security verification
LLMs in Code Security: A Double-Edged Sword
Analyzing vulnerabilities and remediation in AI-assisted coding
AI-Powered News Reliability Assessment
Using LLMs to Evaluate News Publisher Trustworthiness
LLMs as Code Obfuscation Weapons?
Evaluating LLMs' ability to create malware-evading code obfuscations
Navigating with Words
Text-guided geo-localization for location identification
Intelligent Cloud Defense with LLMs
Leveraging AI to anticipate and neutralize cyber threats
Visual Reasoning for Driving Safety
Enhancing VLMs with Retrieval-Based Interleaved Visual Chain-of-Thought
Edge AI for Military Defense Vehicles
Combining LLMs with Edge Intelligence for Secure 6G-Enabled Autonomous Defense
Knowledge-Powered Violence Detection
Building More Interpretable Security Systems Using Graph AI
Diffusion Models Revolutionize Anomaly Detection
A powerful new approach for detecting irregularities in complex data
Weather-Adaptive Maritime Security Systems
Using AI-generated data to overcome weather and category limitations
Personalized AI Surveillance Made Simple
Creating Custom Visual Sensors with Multimodal LLMs
Multi-Agent Framework for KG Error Detection
Leveraging Diverse Perspectives to Enhance Knowledge Graph Security
Smarter Adversarial Testing for Self-Driving Cars
Using LLMs to Identify and Generate Critical Safety Scenarios
Next-Gen Person Re-Identification
Leveraging CLIP to Enhance Security Systems
LLM-Powered Aerial Surveillance
Using AI dialogue systems for active perception and anomaly detection
Smarter Video Search for Security
Context-Aware Retrieval for Enhanced Video Event Detection
Defending Power Grids Against Zero-Day Attacks
Using In-Context Learning to Detect Novel Cyber Threats in Digital Substations
Unmasking Hidden Threats to IoT Devices
How attackers use Tor to exploit cloudless IoT vulnerabilities
Intelligent Network Diagnosis with LLMs
Translating Network Data into Language Model-Readable Semantics
AI-Powered Traffic Scene Understanding
Leveraging Large Visual Language Models for Autonomous Driving
LLMs for Penetration Testing Education
Comparative Analysis of 6 Leading Models for Cybersecurity Training
Enhancing Text-Based Person Search
A novel approach to boost weak positive matches in security applications
Unleashing LLMs on Bitcoin's Digital Trail
A novel approach using AI to interpret cryptocurrency transactions
RepoAudit: AI-Powered Code Security at Scale
Autonomous LLM agent designed for repository-level vulnerability detection
Safeguarding AI Clinicians
Exposing LLM Vulnerabilities in Healthcare Settings
AI-Powered Security Vulnerability Triage
Using LLMs to streamline security bug classification and assessment
Enabling LLM-Powered Fuzzing for Non-Textual Inputs
How G2FUZZ bridges the gap between LLMs and complex input testing
Securing Smart Homes with Synthetic Data
Using LLMs to generate realistic user behavior for security testing
Code Length Matters in Vulnerability Detection
How input size affects LLM security performance
Fault-Tolerant Verification in Distributed Systems
A New Framework for Secure Runtime Verification
Revolutionizing Security with LLMs
How Large Language Models Transform Event Log Analysis
Personalizing Anomaly Detection
A few-shot approach that transforms anomalies to normal patterns
Evaluating Custom GPT Safety
A Framework for Automated Policy Compliance Assessment
LLM-Powered Trading Intelligence
Harnessing AI for Real-Time Market Sentiment Analysis
Hiding Secrets in Plain Text
Enhancing Steganography Security with Large Language Models
Security Risks in AI-Generated Code
A comprehensive analysis across languages and models
Improving LLMs for Financial Trading
Fine-tuning language models with market feedback for better trading signals
Automated Security Fixes for Containers
Using LLMs to Repair Container Misconfigurations
Revolutionizing ADS Testing with Real-World Data
Leveraging multimodal accident data for safer autonomous vehicles
Enhancing Autonomous Driving Safety with LLMs
Using AI to identify and mitigate risks in driving scenarios
SHIELD: Next-Gen APT Detection
Leveraging LLMs for Intelligent Threat Detection & Explanation
AI-Powered Defense Against Phishing Attacks
Automating phishing defense while preserving privacy
AI-Powered Network Penetration Testing
LLMs as Autonomous Security Testers in Enterprise Environments
Enhancing Smart Contract Security Through LLMs
First systematic study of bad practices in Ethereum smart contracts
Smart Ransomware Risk Prioritization
Using historical data to predict and prepare for targeted attacks
Fighting Phishing with AI Intelligence
Leveraging Large Language Models to Detect Malicious Emails
Secure UAV Intelligence: The Aero-LLM Framework
Distributed LLM architecture for enhanced drone security and autonomy
AI Agent Crews in Financial Services
Autonomous LLM-powered systems for modeling and risk management
Cyri: AI-Powered Defense Against Phishing Attacks
A conversational assistant that helps users detect and analyze phishing threats
Securing AI-Generated Code Through Prompt Engineering
Reducing security vulnerabilities by up to 56% in LLM code generation
Improving Bash Command Generation with LLMs
Enhancing security and accessibility of command-line interfaces
Lost in the Code: LLM Vulnerability Detection
How large language models struggle with vulnerability detection in full-size code files
Fighting Modern Slavery with AI
Using LLMs to analyze corporate compliance statements
Measuring LLM Reliability in Security
Benchmarking consistency for cybersecurity applications
Detecting Insider Threats with AI
Using LLMs for Scalable and Ethical Security Analysis
Revolutionizing Security with AI
How LLMs are transforming vulnerability detection in software
CodeQUEST: AI-Powered Code Quality Improvement
Automating code evaluation and enhancement with LLMs
Supercharging Network Security with LLMs
How Large Language Models Can Enhance Network Monitoring
SymGPT: Smarter Smart Contract Auditing
Combining Symbolic Execution with LLMs for Automated Security Verification
Verifying AI-Generated Code
Using SPARK/Ada formal verification to ensure LLM code reliability
SAR Image Interpretation with AI
Advancing Security Applications through Vision-Language Models
Strategic Target Selection in Directed Fuzzing
Optimizing where to fuzz improves vulnerability discovery
Boosting Food Safety AI with Synthetic Data
How ChatGPT-4o-mini enhances LLMs for food hazard detection
Enhancing Surveillance Security with AI
Benchmarking Large Models for Crime Video Analysis
ChatIoT: Smart Security for Smart Devices
Leveraging LLMs to revolutionize IoT security practices
AI-Powered Hazard Source Detection
Autonomous reasoning for critical industrial safety decisions
Smarter Cars Through Collaboration
Enhancing autonomous driving safety with inter-vehicle communication
ScamFerret: AI-Powered Scam Website Detection
Autonomous detection through large language models without training data
Securing RISC-V Processor Designs
Translating Security Assertions Across Architectures
Enhancing Cryptoasset Forensics with AI
Using LLMs to improve attribution tag accuracy and prevent false accusations
Optimizing SMS Spam Detection
Using LLMs to enhance cybersecurity through advanced text classification
Weather Forecasting Revolution via LLMs
Frequency-aware language models for more accurate and efficient predictions
AI-Powered Traffic Monitoring Systems
Enhancing urban mobility through multimodal LLMs and computer vision
Securing DeFi with AI Reasoning
Using LLMs to Detect Cryptocurrency Price Manipulation Attacks
LLMs as Backend Developers: A Security Risk?
Evaluating the security and correctness of LLM-generated backend applications
Voice Profiling: Extracting Demographics from Speech
Using WavLM embeddings to predict speaker attributes from voice alone
AI-Powered Decompilation Breakthrough
Enhancing Security Analysis with LLM-Based Code Reconstruction
Wi-Chat: Revolutionizing Security Through Wi-Fi
Integrating LLMs with Wi-Fi Sensing for Human Activity Recognition
Automating Security Policy Generation
Converting natural language policies to machine-enforceable code with LLMs
On-Device LLMs for Smarter Homes
Efficient dual-role models for intent detection and response generation
LLMs Take On Android Malware
Context-Driven Detection for Enhanced Security
Enhancing Blockchain Security with AI
Fine-tuned LLMs for smart contract vulnerability detection
Simplifying Security: TEE Protection Made Easy
Automating the integration of secure enclaves into existing programs
LLMs in High-Stakes Political Decision-Making
Evaluating AI capabilities in UN security contexts
Controlling What LLMs Learn
A novel approach for supervised learning by revealing and controlling latent features
Securing Smart Contracts with AI
Using LLMs to prevent manipulation attacks through secure partitioning
Context-Aware Chatbots for Smart Environments
Integrating LLMs with real-time user context for personalized interactions
LLM-Powered Security Testing
Semi-Autonomous Penetration Testing with Large Language Models
AI as Cyber Threat Actor
Evaluating LLMs' Offensive Cyber Operation Capabilities
Building Trust in Healthcare AI
Evaluating the trustworthiness of LLMs in clinical applications
AI-Powered Vulnerability Detection
Using LLMs to Automate Medical Device Security Assessment
ZiGong: Specialized AI for Financial Credit Assessment
Combating hallucination in financial decision-making with domain-specific LLMs
Securing the Connected Road Ahead
Using LLMs to Enhance Vehicle Security Through Smarter Key Generation
Securing AI Code Generation
Multi-Model Validation to Mitigate LLM Security Risks
Market Manipulation by AI Agents
How LLM-powered trading bots can influence market sentiment
Navigation-GPT: Revolutionizing Navigation Systems
How LLMs are making navigation more adaptive to unpredictable scenarios
AI-Powered Autonomous Penetration Testing
How LLMs can fully automate IP-to-Shell security testing
Advancing Vehicle Tracking with AI
CLIP-based semantic enhancement without additional annotations
Smart Code Security with Graph Neural Networks
Leveraging heterogeneous GNNs to detect complex software vulnerabilities
LLMs: Revolutionizing News Summarization
Automated solutions for information overload in security contexts
AI-Powered Wildfire Evacuation Prediction
Using LLMs to understand and predict human decision-making during disasters
Enhancing AI for Disaster Response
Using synthetic data to boost common sense reasoning in smaller LLMs
Security Risks in AI-Assisted Development
Understanding LLM vulnerabilities in software engineering workflows
LLMs Revolutionize Program Analysis
Enhancing security through AI-powered code comprehension
AI Guards for Smart Contracts
Using Multi-Agent LLM Systems to Secure Blockchain Applications
Evaluating LLMs for Smart Contract Security
First benchmark for repository-level Solidity code generation
Securing LLMs Against Domain Breaches
A framework for certifying and limiting LLM behavior
ChatReID: Revolutionizing Person Recognition
Interactive Visual Identity Matching Through Advanced Vision-Language Models
AI-Powered Cyber Defense
Transforming Threat Intelligence with Large Language Models
Making AI Safer for Women's Health
Using Semantic Entropy to Reduce Hallucinations in Medical LLMs
Enhancing Fuzz Testing with LLMs
Overcoming reliability challenges in AI-driven security testing
LLMs as Security Guards
Assessing AI's effectiveness in multi-language vulnerability detection
Combating Online Drug Trafficking with AI
Using LLMs to detect illegal drug sales despite limited data
Detecting Privacy Behaviors in Android Code
Improving machine understanding of privacy-relevant code statements
Next-Gen Network Traffic Classification
Comparing Traditional ML, Transformers, and LLMs for Enhanced Security
Advanced Malware Detection Through Memory Analysis
Comparing Traditional ML, Transformers, and LLMs for Security Applications
SyzAgent: LLM-Guided Kernel Fuzzing
Enhancing Security Testing with AI-Powered Mutation
RedChronos: AI-Powered Insider Threat Detection
Using LLMs to analyze enterprise security logs at scale
OmniSec: Closing the Knowledge Gap in Intrusion Detection
Leveraging LLMs to Automate Provenance-based Security Analysis
AttackSeqBench: Benchmarking Large Language Models' Understa...
By Javier Yong, Haokai Ma...
Securing Critical Infrastructure with AI
Using LLMs to Make IoT Security Systems Explainable
COSINT-Agent: Revolutionizing Intelligence Gathering
A Knowledge-Driven Multimodal Approach to Chinese OSINT
A 262 TOPS Hyperdimensional Photonic AI Accelerator powered ...
By Christos Pappas, Antonios Prapas...
Benchmarking LLMs and LLM-based Agents in Practical Vulnerab...
By Alperen Yildiz, Sin G. Teo...
KidneyTalk-open: No-code Deployment of a Private Large Langu...
By Yongchao Long, Chao Yang...
Edge-Based Malware Detection with Lightweight LLMs
Optimizing security for resource-constrained edge devices
LLMs as Your IoT Automation Hub
Enabling Seamless Natural Language Control for IoT Devices
Garbage In, Garbage Out: LLM Security Research
Why Quality Matters in Security Vulnerability Datasets
Control Flow-Augmented Decompiler based on Large Language Mo...
By Peipei Liu, Jian Sun...
LLaMA 3.2: The New Frontier in Vulnerability Detection
Leveraging advanced LLMs to identify software security flaws
Wi-Fi Sensing Beyond Boundaries
Addressing generalization challenges in wireless sensing technology
Revolutionizing Medical Image Re-Identification
A unified approach across all medical imaging modalities
Multimodal Stock Prediction
Combining News Text and Price Data for Better Market Forecasting
Securing Software Through Smart Debloating
Using LLMs to Enhance Security by Removing Unnecessary Code
Supercharging Security with AI-Powered Bug Detection
How LLMs can transform static analysis for critical systems
Securing LLMs in Cybersecurity
New dataset to evaluate and mitigate AI safety risks
CASTLE: Benchmarking Dataset for Static Code Analyzers and L...
By Richard A. Dubniczky, Krisztofer Zoltán Horvát...
Scaling Person Identification with AI Annotations
Using AI to Model Human-like Diversity in ReID Systems
Securing Smart Contracts Against Numerical Vulnerabilities
LLM-Enhanced Detection of Mathematical Flaws in Blockchain Applications
Enhancing Object Re-ID with Text Intelligence
A novel text-integrated approach to multi-modal object recognition
Vulnerability Detection: From Formal Verification to Large L...
By Norbert Tihanyi, Tamas Bisztray...
Leveraging LLM Hallucinations for Rust Security
Novel approach to detect vulnerabilities in safety-focused Rust code
Falcon: Revolutionizing Remote Sensing with AI
A foundation model that transforms how we analyze satellite imagery
Unlocking Assembly Code Comprehension with AI
A new approach to making assembly code accessible through LLMs
AI-Powered Highway Emergency Response
Integrating LLMs into Traffic Incident Management
Enhancing LLMs for Code Security
Using Bridging Predicates to Fix Static Analysis Alerts
Foundation Models for IoT Event Detection
Advancing CPS-IoT security through advanced event reasoning
360° Action Detection for Mission-Critical Training
AI-powered video analysis for enhanced security training and debriefing
AI-Powered Travel Safety
Personalized Safety Advice Through Retrieval-Augmented LLMs
Decoding the Blockchain's Black Box
Automating Comments for Smart Contracts Without Source Code
Mapping Android Threats with MITRE ATT&CK
Enhanced malware intelligence through TTP analysis
LLMs as Privacy Policy Analyzers
Automating legal document analysis with AI
Advancing Speaker Verification Security
Enhancing biometric authentication with adversarial training techniques
AI-Powered Secure Code Review
Revolutionizing DevSecOps with GitHub-Integrated Vulnerability Detection
AI Security Threat Assessment
Evaluating LLM Agents' Ability to Exploit Web Vulnerabilities
Bridging C to Rust: Smarter Migration
Using program analysis and LLMs for safer, more maintainable translations
VulnSage: Smart Vulnerability Detection
Using LLMs for Zero-Shot Code Security Analysis
AI-Enhanced Credit Default Prediction
How ChatGPT refines loan assessments for better risk analysis
Leveraging LLMs for Advanced Threat Detection
A semantic-augmented approach to identify APTs through provenance analysis
Leveraging LLMs for Network Security
A new paradigm for intelligent threat detection
Boosting Typosquatting Detection with AI
Using Large Language Models to Combat Sophisticated URL Deception
The LLM Reliability Gap in Cybersecurity
Evaluating LLMs for Cyber Threat Intelligence: Warning Signs Ahead
Aud-Sur: Next-Gen Audio Surveillance
An AI-powered audio analysis assistant for security applications
Social Media Intelligence for Disaster Response
Leveraging LLMs to Extract Stakeholder-Specific Crisis Insights
CyberBOT: Enhancing Cybersecurity Education with AI
Ontology-Grounded Retrieval for Trustworthy Technical Learning
AI-Powered Threat Intelligence
Using LLMs to Automate Cybersecurity Response
Harnessing LLMs for Android Malware Detection
A new benchmarking framework evaluates code LLMs in cybersecurity contexts
MaLAware: AI-Powered Malware Comprehension
Translating Complex Malware Behaviors into Human-Readable Narratives
Strategic LLM Integration for Finance
A framework for responsible AI innovation in financial services
Revolutionizing Digital Forensics with AI
How Large Language Models Are Transforming Investigative Security
Security Vulnerabilities in Medical AI Agents
Exposing cyber attack risks in healthcare LLM applications
AI-Powered Attack Pattern Generation
Using LLMs to enhance security testing for Industrial Control Systems
Revolutionizing Financial Risk Management with LLMs
Real-time cross-asset monitoring for enhanced market risk assessment
AI-Powered Risk Management
Enhancing Derivatives Trading with LLM-Based Sentiment Analysis
LLMs as Financial Advisors: Proceed with Caution
Evaluating AI agents in high-stakes financial decision-making
Enhancing Cyber Threat Intelligence with AI
A new human-annotated dataset for automated threat analysis
AI-Powered Security for Hardware Designs
Leveraging LLMs to Enhance Information Flow Tracking
LLMs in Safety-Critical Applications
Evaluating Retrieval Augmented Generation for Transportation Safety
LLMs as Security Defenders
Transforming cybersecurity through advanced language models
DeepGreen: Catching Corporate Greenwashing
AI-powered detection system for environmental claim verification
AI-Powered XSS Attack Detection
Using LLMs to outsmart sophisticated web attacks
AI-Powered Hardware Security
How LLMs are transforming secure hardware design
LLMs for Vulnerability Classification
Using AI to automate security risk scoring
Evaluating AI's Cybersecurity Expertise
A Fine-Grained Framework for Assessing LLMs in Cybersecurity
