𝑨𝒔𝒔𝒆𝒎𝒃𝒍𝒂𝒈𝒆: 𝑨𝒖𝒕𝒐𝒎𝒂𝒕𝒊𝒄 𝑩𝒊𝒏𝒂𝒓𝒚 𝑫𝒂𝒕𝒂𝒔𝒆𝒕 𝑪𝒐𝒏𝒔𝒕𝒓𝒖𝒄𝒕𝒊𝒐𝒏 𝒇𝒐𝒓 𝑴𝒂𝒄𝒉𝒊𝒏𝒆 𝑳𝒆𝒂𝒓𝒏𝒊𝒏𝒈 Compiling projects GitHub . Randomize the compiler version & settings. We are building 𝑡ℎ𝑒 tool for making datasets for research! 2 years work!

15 UMBC CSEE students successfully defended their PhD dissertations this year so far, bringing the total number of PhDs the department has produced to 426. See the list, mentors, and dissertation titles via the link below. Congrats to the new doctors! csee.umbc.edu/phd-graduates/

I love this for bitcoin belivers

Helping analysts with their reverse engineering work and finding similar functions is a problem. A lot of existing literature doesn't really work on real data. We can get better results by being dumber! NeurIPS Conference #NeurIPS2024 Booz Allen Hamilton w/ Kristopher Micinski -- DEFUNCT Richard Ż

To label your own malware collection, download ClarAVy here! github.com/FutureComputin…

A new EMBER malware benchmark has been released, with new datasets and 14 baseline LightGBM models. It’s one of the best open-source resources for malware classification and adversarial-testing experiments.

EMBER2024 -- A Benchmark Dataset for Holistic Evaluation of Malware Classifiers. arxiv.org/abs/2506.05074

tinyurl.com/27l4fqdp Researchers unveil EMBER2024, a groundbreaking dataset advancing malware analysis. With diverse file formats, tasks, and undetected evasive files, it empowers robust classifier evaluation and fosters new research opportunities in malware detection.

Lead by RJ 🐢 , #EMBER24 has arrived SIGKDD 2025 #KDD25, the best, most open, and versatile malware detection benchmark ever! w/ Richard Ż Phil Roth Hyrum Anderson & others, let's try to barely summarize all the new things you can do now! Booz Allen Hamilton CrowdStrike Cisco 🧵👇

Syracuse University Tonight at the poster session come see me, RJ 🐢 presenting EMBER3 Phil Roth Hyrum Anderson Richard Ż CrowdStrike Booz Allen Hamilton Cisco

EMBER2024 is a dataset of metadata, labels, and calculated features for more than 3.2 million malicious and benign files. We've released it in support of training and evaluating ML classifiers to detect and categorize malware. Read more about it here! crowdstrike.com/en-us/blog/emb…

i made a simple RL environment based on the EMBER2024 capa dataset from RJ 🐢. this is also my first time using the Prime Intellect environments hub. it's got lots of different environments if you are curious about the possibilities. app.primeintellect.ai/dashboard/envi…