Attack and Defense Techniques in Large Language Models: a Survey and New Perspectives

Large Language Models LLMs have become central to numerous natural language processing tasks, but their vulnerabilities present significant security and ethical challenges. This systematic survey explores the evolving landscape of attack and defense techniques in LLMs. We classify attacks into...

Exploit for Unrestricted Upload of File with Dangerous Type in Sap Netweaver

CVE-2025-31324 Burp Suite Extension Overview This Python-b...

Exploit for SQL Injection in Teampass

CVE-2023-1545 Simple SQL Injection Python script for Teamp...

PEGASUS-NEO - A Comprehensive Penetration Testing Framework Designed For Security Professionals And Ethical Hackers. It Combines Multiple Security Tools And Custom Modules For Reconnaissance, Exploitation, Wireless Attacks, Web Hacking, And More

| \ | \ | | | | / / |/ / | | | / | | | | / / | | | \ \ || \ \ |\ | || |, |,|/,|/| | |/ ███▄ █ ▓█████ ▒█████ ██ ▀█ █ ▓█ ▀ ▒██▒ ██▒ ▓██ ▀█ ██▒▒███ ▒██░ ██▒ ▓██▒ ▐▌██▒▒▓█ ▄ ▒██ ██░ ▒██░ ▓██░░▒████▒░ ████▓▒░ ░ ▒░ ▒ ▒ ░░ ▒░ ░░ ▒░▒░▒░ ░ ░░ ░ ▒░ ░ ░ ░ ░ ▒ ▒░ ░ ░ ░ ░ ░ ░ ░ ▒ ░ ░ ░ ░ ░ PEGASUS-NEO...

Exploit for CVE-2025-3102

CVE-2025-3102 🛠️ SureTriggers Exploit Script Script ini diguna...

cleverjob24.de Cross Site Scripting vulnerability OBB-4043255

Following the coordinated and responsible vulnerability disclosure guidelines of the ISO 29147 standard, Open Bug Bounty has: a. verified the vulnerability and confirmed its existence; b. notified the website operator about its existence. Technical details of the vulnerability are currently hidde...

“Nudify” deepfakes stored unprotected online

Yesterday, we told you about how millions of pictures from specialized dating apps had been stored online without any kind of password protection. Now it's the turn of an AI "nudify" service. A researcher, famous for finding unprotected cloud storage buckets, has uncovered an unprotected AWS buck...

Exploit for Path Traversal in Splunk

CVE-2024-36991 - Splunk Path Traversal Proof of Concept for...

Exploit for Improper Restriction of Excessive Authentication Attempts in Fortinet Fortiauthenticator

CVE-2023-26208 Exploit Automation Para Fins Educacionais 🚨 📌...

Exploit for CVE-2025-30208

CVE-2025-30208-LFI !IMPORTANT Disclaimer This exploit...

Exploit for Deserialization of Untrusted Data in Apache Tomcat

CVE-2025-24813-PoC === CVE-2025-24813 affects Apache Tomcat - i...

The Hidden Costs and Ethical Pitfalls of Content Scraping

Read about the significant hidden costs and ethical pitfalls of content scraping — and learn how to protect your website...

⚡ THN Weekly Recap: Router Hacks, PyPI Attacks, New Ransomware Decryptor, and More

From sophisticated nation-state campaigns to stealthy malware lurking in unexpected places, this week's cybersecurity landscape is a reminder that attackers are always evolving. Advanced threat groups are exploiting outdated hardware, abusing legitimate tools for financial fraud, and finding new...

Under The Hoodie: The Pen Test Diaries

Breaking In So You Don’t Have To Each year, Rapid7 penetration testers conduct over 1,000 security assessments, pushing boundaries to expose vulnerabilities before the bad guys do. The mission? Get in, escalate privileges, and own the environment—physically, digitally, or sometimes just by...

Analyzing DeepSeek’s System Prompt: Jailbreaking Generative AI

DeepSeek, a disruptive new AI model from China, has shaken the market, sparking both excitement and controversy. While it has gained attention for its capabilities, it also raises pressing security concerns. Allegations have surfaced about its training data, with claims that it may have leveraged...

Italy Bans Chinese DeepSeek AI Over Data Privacy and Ethical Concerns

Italy's data protection watchdog has blocked Chinese artificial intelligence AI firm DeepSeek's service within the country, citing a lack of information on its use of users' personal data. The development comes days after the authority, the Garante, sent a series of questions to DeepSeek, asking...

HackGATE: Setting New Standards for Visibility and Control in Penetration Testing Projects

Imagine receiving a penetration test report that leaves you with more questions than answers. Questions like, "Were all functionalities of the web app tested?" or " Were there any security issues that could have been identified during testing?" often go unresolved, raising concerns about the...

API Security’s Role in Responsible AI Deployment

By now, you will almost certainly be aware of the transformative impact artificial intelligence AI technologies are having on the world. What you may not be aware of, however, is the role Application Programming Interfaces APIs are playing in the AI revolution. The bottom line is that APIs are...

Exploit for CVE-2024-9290

CVE-2024-9290 Exploit Tool | Super Backup & Clone Vulnerabilit...

Exploit for Insufficient Verification of Data Authenticity in Rarlab Winrar

CVE-2023-38831 Exploit Proof-of-Concept Overview This rep...