Inside The Lab HarfangLab's tech Blog
2024 Threatscape report
As we step into 2024, we anticipate a year that is poised to set several significant precedents. In this blogpost, we provide our Threatscape report, presenting our predictions for the global threats that lie ahead in the upcoming year. These…
An introduction to reverse engineering .NET AOT applications
About a month ago, we started seeing reports on activities from DuckTail , a cybercrime outfit reportedly based in Vietnam. Detonating one of the samples, we observed that a new account was being created on the analysis machine, followed by…
Machine Learning to identify malicious strings in a file
Why bother with strings? When analyzing a new sample found “inthewild”, it may make sense to extract the strings within it to identify IP addresses, domains, log files or C&C server signatures. For example, if an Artificial Intelligence model such…
How many slices of pizza do you need to appear in MITRE?
“We don’t see you in MITRE.” “Your solution hasn’t even been benchmarked, so how can anyone know what you’re REALLY worth?” “Anyway, it’s impossible for a French player to be as good as the Americans…” … okay, okay, that’s enough…
Taskloader at the root of a Pay-per-Install infection chain
In June 2023, we’ve observed multiple alerts that seemingly came from different sources. A quick search through our telemetry allowed us to identify multiple infected machines across our clients. Although they would sometimes present different behaviour, the initial infection vector…
Simulate the activity of a brute-force attack
For the purpose of testing an unsupervised anomaly detection algorithm, we need a dataset with both benign and malicious authentication activities. We already have access to benign data, but we lack malicious attack events.</p> The question we will try to…
AI: Deep Learning & batch normalization
Embedding images and executable files Embedding images into a lower-dimensional representation is a blooming research field in Deep Learning. With a small vector representation of each image, many new tasks can be easily done afterward such as zero-shot learning and…
Malwares detection: an innovative approach based on Deep Learning
Hibou is a malware detection module powered by deep learning. It works on Windows executable files (PE files) and gives, for each sample, a “score of potential maliciousness”. This state-of-the-art deep learning method to detect malicious files is now embedded…
Generate large-scale attacks without a fleet of machines
One of the recurring issues in artificial intelligence is gathering enough data to train your model. In our case, working with windows event logs is not an easy task, as there are no available datasets that correspond exactly to what…
PowerShell: the story of collaboration between AI and CTI teams
At HarfangLab, the Artificial Intelligence (AI) and Cyber Threat Intelligence (CTI) teams can combine their strengths to prevent and detect threats. In the past year, we have worked on all of the aspects of AI to enhance our malware detection,…
How to write idiomatically in RUST magically fixed my bugs
When using compiled languages, code cannot be run if it does not pass the compilation step, and for this reason, the compiler sometimes gets in your way. Sometimes, the compiler refuses the quick-and-dirty change you made to test an idea.…
HL-AI Binaries depending on version
Description Ashley Binaries is a malware detection module powered by machine learning and deep learning. It works on executable files (PE files for windows and ELF for linux) and gives, for each sample, a “score of potential maliciousness”. …