JFrog Security

@JFrogSecurity

The JFrog Security Research Team empowers developers and companies to excel by identifying, prioritizing, and mitigating software risks.

USA / Israel

research.jfrog.com

انضم في نوفمبر 2017

1Kالمنشورات 3Kالمتابعون 300المتابَعون

قد يعجبك

@Education_Ire

@S0ufi4n3

@ptswarm

@urlscanio

@GetApp

@JCyberSec_

@_wald0

@futureofprivacy

@JRoosen

@IdoNaor1

@IoT_SF

@tastelikekanndy

@nagoyajorge117

@HikindPinny

@DefenceBird

JFrog Security

@JFrogSecurity

١٠ أكتوبرم

📣 #CyberSecurityAwareness Mini-Series: "Hunting Malicious ML Models" Part 5, THE FINALE asks... 🫨 Can "Safe" ML Models be Weaponized?⚡️ ✨ Let’s start by defining what a “Safe” Models is: Safe models were created to reduce this malicious code execution risk we discussed in…

JFrog Security

@JFrogSecurity

٩ أكتوبرم

📣 #CyberSecurityAwareness Mini-Series: "Hunting Malicious ML Models" Part 4 is all about... 🏃🏻 Library Mitigations and How They Can be Bypassed 🏃🏻 Scanners cannot take full responsibility for protecting against malicious models. This has pushed #ML Python libraries to add…

JFrog Security

@JFrogSecurity

٨ أكتوبرم

📣 #CyberSecurityAwareness Mini-Series: "Hunting Malicious ML Models" Part 3 poses the question... How do scanners work and why do they generate False Positives (FPs) + False Negatives (FNs)? 🤔 ❎ False Positives (FPs) ❎ Looking at the numbers, other scanners on Hugging Face…

JFrogSecurity's tweet image. 📣 #CyberSecurityAwareness Mini-Series: "Hunting Malicious ML Models" Part 3 poses the question...

How do scanners work and why do they generate False Positives (FPs) + False Negatives (FNs)? 🤔

❎ False Positives (FPs) ❎
Looking at the numbers, other scanners on Hugging Face…

JFrog Security أعاد

JFrog

@jfrog

٧ أكتوبرم

📣 #CyberSecurityAwareness Mini-Series: "Hunting Malicious ML Models" Part 2 talks about the 3 most common model threats 👇🏼 🔹 PyTorch-Malcode (1,263 files detected) #PyTorch models’ default save and load functionalities rely on Pickle serialization and deserialization.…

jfrog's tweet image. 📣 #CyberSecurityAwareness Mini-Series: "Hunting Malicious ML Models" Part 2 talks about the 3 most common model threats 👇🏼

🔹 PyTorch-Malcode (1,263 files detected)

#PyTorch models’ default save and load functionalities rely on Pickle serialization and deserialization.…

JFrog Security أعاد

JFrog

@jfrog

١ أكتوبرم

Too many #security tools are creating more problems than they solve. This #CyberSecurityAwarenessMonth, JFrog Field CISO, Paul Davis, breaks down why a fragmented defense can leads to higher costs, slower remediation, and a weaker security posture. Learn how to move from silos…

jfrog's tweet image. Too many #security tools are creating more problems than they solve.

This #CyberSecurityAwarenessMonth, JFrog Field CISO, Paul Davis, breaks down why a fragmented defense can leads to higher costs, slower remediation, and a weaker security posture.

Learn how to move from silos…

JFrog Security أعاد

JFrog

@jfrog

١ أكتوبرم

🔐 October marks #CybersecurityAwarenessMonth! We kicked it off yesterday with our first miniseries: “Hunting Malicious ML Models – Insights from Analyzing 1.5M Models.” And all month long, we'll be sharing new research, blogs, & webinars as your go-to resources for uncovering…

jfrog's tweet image. 🔐 October marks #CybersecurityAwarenessMonth!

We kicked it off yesterday with our first miniseries: “Hunting Malicious ML Models – Insights from Analyzing 1.5M Models.”

And all month long, we'll be sharing new research, blogs, &amp; webinars as your go-to resources for uncovering…

JFrog Security

@JFrogSecurity

٣٠ سبتمبرم

Our security team uncovered a malicious PyPI package called SoopSocks, which disguises itself as a SOCKS5 proxy but behaves like a backdoor. Our research revealed that it installs persistence via Windows services and scheduled tasks, modifies firewall rules, silently executes…

JFrog Security

@JFrogSecurity

٣٠ سبتمبرم

JFrog is getting a jumpstart on #CyberSecurityAwareness Month! 🚨 We're kicking it off with our 1st miniseries: "Hunting Malicious ML Models - Insights from Analyzing 1.5M Models" 👇🏼 Here's what you need to know👇🏼 1. HUGE growth in malicious ML models published on Hugging Face…

JFrogSecurity's tweet image. JFrog is getting a jumpstart on #CyberSecurityAwareness Month!

🚨 We're kicking it off with our 1st miniseries: "Hunting Malicious ML Models - Insights from Analyzing 1.5M Models"

👇🏼 Here's what you need to know👇🏼

1. HUGE growth in malicious ML models published on Hugging Face…

JFrog Security

@JFrogSecurity

١٦ سبتمبرم

🚨 NEW APP SECURITY ALERT: 🚨 Shai-Hulud npm supply chain attack – 164 new compromised packages detected by JFrog Security Researchers. Following the recent compromise of the nx packages and another wave targeting popular packages, the npm registry was hit by a third…