A YARA rule is easy to share. The malware sample used to prove that the rule works often is not. That gap matters in detection engineering. Teams need positive fixtures to test scanners, alerting, incident-response automation, disaster-recovery workflows, and CI pipelines. Using live malware for those tests creates a separate operational problem: isolated infrastructure, handling controls, retention policy, and specialist oversight. A useful test artifact must satisfy the rule without reproducing the behavior of the malware that originally triggered it. ...
Emanuel Valente
Security engineer and researcher working on defensive AI, machine learning security, and detection engineering.
- Principal Cybersecurity Engineer at iFood
- PhD candidate at the University of São Paulo (USP)
- Research interests: adversarial ML, malware analysis, and security automation
iFood AI Security Meetup: Bringing the Community Together
On December 5, 2025, I helped organize the first iFood AI Security Meetup at our Campinas office. It came together quickly, without a budget: an idea among friends and colleagues from universities and the participating companies who wanted to get people in the same room to talk about AI security. Seeing researchers, students, and security practitioners share ideas throughout the day made the effort worth it. The full write-up on the iFood Security Blog introduces the speakers and includes recordings of the talks. They cover security in machine learning, attacks through MCP servers, anomaly detection at scale, and injection attacks against LLMs. If you couldn’t make it to Campinas, you can watch the sessions there. ...
DoH Deception: Testing the Robustness of ML-Based Tunnel Detection
High accuracy is not the same thing as robustness.[1] That was the question behind my master’s research on DNS over HTTPS (DoH) tunnel detection. Several machine-learning classifiers reported excellent performance when evaluated on conventional train/test splits. But an attacker does not need to draw another sample from the same dataset distribution. They can change how a tunnel behaves, observe the detector’s output, and search for a traffic pattern that still carries their data while the classifier labels the flow as benign.[1] ...
Prompt Injection: Exploring, Preventing & Identifying Langchain Vulnerabilities
Introduction Hey there, cyber enthusiasts! 🚀 This article originally appeared on the iFood Security Blog, where I delve into the intricacies of LLM (Large Language Models) and their implications for cybersecurity. I encourage readers to view the original article for a deeper dive into this subject. The following is an adaptation of that content, tailored for this blog audience, with additional insights and perspectives. Additionally, The OWASP Top 10 for Large Language Model Applications project has included this material as educational resources. If you are considering deep in this area, check the content and familiarize yourself with this OWASP project. ...