From Prompt Injections to Protocol Exploits: Threats in LLM-Powered AI Agents Workflows
Paper
• 2506.23260 • Published
Mohamed Amine Ferrag
Ferrag
AI & ML interests
None yet
Recent Activity
authored
a paper
about 12 hours ago
From Prompt Injections to Protocol Exploits: Threats in LLM-Powered AI
Agents Workflows authored
a paper
about 12 hours ago
The Hidden DNA of LLM-Generated JavaScript: Structural Patterns Enable
High-Accuracy Authorship Attribution authored
a paper
about 12 hours ago
AgentDrive: An Open Benchmark Dataset for Agentic AI Reasoning with LLM-Generated Scenarios in Autonomous Systems Organizations
None yet
authored 3 papers about 12 hours ago
authored a paper 7 days ago
authored 7 papers 8 months ago
A New Era in Software Security: Towards Self-Healing Software via Large Language Models and Formal Verification
Paper
• 2305.14752 • Published
• 1
CyberMetric: A Benchmark Dataset for Evaluating Large Language Models Knowledge in Cybersecurity
Paper
• 2402.07688 • Published
• 2
Generative AI and Large Language Models for Cyber Security: All Insights You Need
Paper
• 2405.12750 • Published
• 3
Vulnerability Detection: From Formal Verification to Large Language Models and Hybrid Approaches: A Comprehensive Overview
Paper
• 2503.10784 • Published
• 1
From LLM Reasoning to Autonomous AI Agents: A Comprehensive Review
Paper
• 2504.19678 • Published
• 3
Reasoning Beyond Limits: Advances and Open Problems for LLMs
Paper
• 2503.22732 • Published
I Know Which LLM Wrote Your Code Last Summer: LLM generated Code Stylometry for Authorship Attribution
Paper
• 2506.17323 • Published
• 5