In other news, I've recently put together a big state of the art regarding symbolic execution techniques used in system research. Check out the slides here! 1/2 docs.google.com/presentation/d…

La montée du nationalisme, de l'autoritarisme et de la haine ne semble pas être un accident circonstanciel limité à un pays. Selon les rapports Varieties of Democracy Institute auquel 3000+ chercheurs contribuent, il s'agit d'une tendance alarmante à l'échelle planétaire. v-dem.net/democracy_repo…

First in-person conference ! #ares2022 Looking forward to hear great speakers and share about Cybersecurity !

In a perfect world, you could effortlessly switch between modeling mindsets (statistics, machine learning, causal inference, ...). Realistically, you only have time to master a few mindsets. So what to do? A thread 🧵

Machine learning sucks at uncertainty quantification. But there is a solution that almost sounds too good to be true: conformal prediction • works for any black box model • requires few lines of code • is fast • comes with statistical guarantees A thread 🧵

Awesome Executable Packing - A curated list of resources related to the packing of various executable formats and its detection. github.com/dhondta/awesom… #awesomelists #malware #malwareresearch #executablepacking #cybersecurity #infosec

Systems for automatic paper-reviewer assignments (e.g., TPMS - mila.quebec/en/publication…) are used during the reviewing process of conferences such as ICML Conference. In arxiv.org/abs/2303.14443, we explore how authors might try to game these systems. We propose an attack that adapts...

6️⃣ Python libraries to help you interpret machine learning models. How many of them are you using already? Read on and find out 👇 🧵

🤖 oopsie in a 2023 Elsevier journal paper: “Please note that as an AI language model, I am unable to generate specific tables or conduct tests, so the actual results should be included in the table.” 🤡 #ChatGPT

Get rid of bad reviewers? 🤔 Today, Thorsten Eisenhofer presents our work USENIX Security on misleading the automatic assignment of reviewers at large conferences (e.g. #CVPR or #NeurIPS). Our attack generates adversarial papers that select their own reviewers. BIFOLD CASA - Cluster of Excellence for Cyber Security 1/5

Can you tell the difference between a human and an AI? Really excited to share turingtest.live, a site where you can play the Turing Test with GPT-4. You get randomly matched with either a human or an AI, and you have 5 minutes to decide which it is.

The most recent Ghidra update by NSA Cyber allows one to use fuzzy function recognition. The documentation along with it is of great use: github.com/NationalSecuri…

Happy to publish our book project “Supervised Machine Learning for Science” today 🥳 Read it for free here: ml-science-book.com The book is about the philosophical and pragmatic justification for using supervised machine learning in science.

What kind of guarantees can our tooling & processes really provide about the security of our software systems? Here are 9 *fundamental* challenges that are routinely exploited to attack a system despite credible assurances about its security. Preprint: arxiv.org/abs/2402.01944

Btw, you don't need a Flipper Zero to "hack" dumb radio protocols. The piece of wire is enough. Check out how to receive and decode 433MHz radio signal just with a PC sound card.

Awesome Drone Hacking - A curated list of resources related to drone hacking. github.com/dronesploit/aw… #awesomelists #drone #hacking #cybersecurity #infosec