📣 Exciting News! 📚 NERO project’s free #CybersecurityTraining for SMEs is now live on the @DigitalSkillsEU!
🛡️ Designed to help #SMEs navigate today’s #CyberRisks, the training provides practical tools to strengthen your organisation’s #DigitalResilience and boost #CyberAwareness.
⚙️ Built on insights from leading #Cybersecurity research and industry experts, the curriculum includes 9️⃣ scenario-based modules that let learners make decisions in realistic cybersecurity situations.
💻 Check out 4️⃣ featured #FreeTraining resources:
✔️ Module 3: #SocialEngineering – Learn how to spot and defend against common #CyberAttack techniques.
✔️ Module 4: #NetworkSecurity & Penetration Testing for SMEs – Hands-on training for #NetworkProtection and testing.
✔️ Module 5: #SoftwareSecurity & #CodeAuditing – Gain practical skills in secure coding, vulnerability detection, and #DevSecOps practices.
✔️ Module 9: #KIOKU – #Gamified Scenario-based Training – Explore cybersecurity through interactive simulations.
🚀 Don’t miss this chance to stay ahead of #CyberThreats and equip your team with essential #DigitalSkills!
📄 Read the full #PressRelease & learn more:
🔗tinyurl.com/4nhzmvbm
Co-RedTeam - Orchestrated Security Discovery and Exploitation with LLM Agents - arxiv.org/pdf/2602.02164 by @Google
We propose Co-RedTeam, a security-aware multi-agent framework for automatic software vulnerability discovery and exploitation, explicitly designed to overcome core limitations of existing LLM-based security systems, namely brittle single-shot reasoning, lack of execution-grounded validation, and the inability to learn from prior attacks.
Inspired by how human security experts conduct red teaming, Co -RedTeam tightly integrates four capabilities essential for realistic cybersecurity tasks: security grounding, code-aware analysis, execution-driven reasoning, and experience accumulation.
Authors: Pengfei He, Ash Fox, Lesly Miculicich, @stfn42, Daniel Fabian, Burak Gokturk, @tangjiliang, @chl260, @tomaspfister, Long T. Le - @michiganstateu#AISecurity#LLMAgents#RedTeaming#VulnerabilityResearch#AppSec#SecureCoding#AIForSecurity#OffensiveSecurity#AgenticAI#CybersecurityResearch#CodeAuditing#ExploitDevelopment
AI Security Research - 17 papers - July 2025
taleliyahu.medium.com/ai-sec…
This is my selected list of 17 research papers covering LLM security, agent vulnerabilities, MCP abuse, backend flaws, smart contract analysis, and red teaming benchmarks.
1️⃣ We Urgently Need Privilege Management in MCP: A Measurement of API Usage in MCP Ecosystems
2️⃣ TRiSM for Agentic AI: A Review of Trust, Risk, and Security Management in LLM-based Agentic Multi-Agent Systems
3️⃣ AIRTBench: Measuring Autonomous AI Red Teaming Capabilities in Language Models
4️⃣ A Survey of LLM-Driven AI Agent Communication: Protocols, Security Risks, and Defense Countermeasures
5️⃣ RepoAudit: An Autonomous LLM-Agent for Repository-Level Code Auditing
6️⃣ Decompiling Smart Contracts with a Large Language Model
7️⃣ Dynamic Risk Assessments for Offensive Cybersecurity Agents
8️⃣ When LLMs Autonomously Attack
9️⃣ ETrace: Event-Driven Vulnerability Detection in Smart Contracts via LLM-Based Trace Analysis
🔟 BaxBench: Can LLMs Generate Correct and Secure Backends?
1️⃣1️⃣ Autonomous AI-based Cybersecurity Framework for Critical Infrastructure
1️⃣2️⃣ SafeGenBench: A Benchmark Framework for Security Vulnerability Detection in LLM-Generated Code
1️⃣3️⃣ Red Teaming AI Red Teaming
1️⃣4️⃣ From Prompt Injections to Protocol Exploits: Threats in LLM-Powered AI Agent Workflows
1️⃣5️⃣ Vulnerability Detection Model using LLM and Code Chunk
1️⃣6️⃣ Trivial Trojans: How Minimal MCP Servers Enable Cross-Tool Exfiltration of Sensitive Data
1️⃣7️⃣ Security Challenges in AI Agent Deployment: Insights from a Large Scale Public Competition
#AISecurity#RedTeaming#MCP#LLMAgents#SmartContracts#CodeAuditing#ProtocolSecurity#BackendSecurity#PromptInjection#MemoryPoisoning#SupplyChainSecurity#AgentSecurity#CTF#VulnerabilityDetection#AutonomousAgents#LLMSecurity
As a fast-growing #startup, our team strives to move quickly to deploy necessary #code changes. 💨
A big shout-out to our #DevOps Engineer, @davegallant_, for providing a thorough guide of our #CodeAuditing process for #SOC2 compliance. ✅
Read more! 👇
bit.ly/3hiwMLL
We want to hear your stories of how you took advantage of #FreeApril!
Pluralsighters, what new skill or tool did you learn this month—and how are you putting it to use?