🔥 How to attack Large Language Models using Poetry

What is poetry to you? For many, it is a vehicle for emotion, imagination, and reflection. Yet poetry can also play an unexpected role in the context of Artificial Intelligence (AI). What if we told you that poetry can be used to attack Large Language Models (LLMs)? In this article, we examine the study on adversarial poetry, focusing on its underlying mechanism, its effectiveness, and…

🔗 Link 👉 https://8bitsecurity.com/posts/how-to-attack-large-language-models-using-poetry/
#cybersecurity #infosec

[🇮🇹 ]😈 Il ransomware Lynx
Lynx si diffonde attraverso molteplici vettori di attacco e, una volta ottenuto l’accesso al sistema, procede a cifrare i file utilizzando l’algoritmo AES, lasciando intatti solo quelli di sistema. Una peculiarità che lo distingue da molte altre varianti è la modalità con cui diffonde la nota di riscatto: Lynx invia il messaggio a tutte le stampanti presenti nella rete, un espediente inusuale che aggiunge ulteriore pressione alla vittima.

🔗https://blog.8bitsecurity.com/2025/03/24/analisi-approfondita-del-ransomware-lynx/

💣 Q-Day: Why Current Cryptography Is Not Ready for a Quantum Adversary

The evolution of quantum computing poses a direct threat to the cryptographic algorithms most widely used today. Schemes such as RSA and Diffie-Hellman, which form the backbone of modern communications security, were not designed to withstand adversaries equipped with sufficiently advanced quantum capabilities. To address this scenario, two distinct approaches are em…

🔗 Link 👉 https://8bitsecurity.com/posts/q-day-why-current-cryptography-is-not-ready-for-a-quantum-adversary/
#cybersecurity #infosec

🔎 Chain-Of-Thoughts Hijacking against Reasoning Models

Large Reasoning Models are a class of artificial intelligence systems designed to solve complex problems by combining natural language understanding with explicit logical reasoning.

The new introduced attack is named Chain-of-Thought Hijacking, a simple jailbreak where harmless reasoning is prepended before a harmful instruction.

🔗 Link 👉️ https://8bitsecurity.com/posts/chain-of-thoughts-hijacking-against-reasoning-models/

#cybersecurity #infosec

💀 Threat Hunting Cobalt Strike The Final Guide: From the Depths of Beaconing to C2 Infrastructure

A tool that needs no introduction, widely favored by threat actors and extensively scrutinized by defenders. After years of observing and analyzing real-world compromises, the time has come to produce what we believe to be the most compreh…

🔗 Link 👉 https://8bitsecurity.com/posts/threat-hunting-cobalt-strike-the-final-guide-from-the-depths-of-beaconing-to-c2-infrastructure/
#cybersecurity #infosec

💀 Threat Hunting su Cobalt Strike: dalle viscere del beaconing all’infrastruttura C2

Un tool che non ha bisogno di presentazioni, ampiamente utilizzato dai threat actor e costantemente analizzato dai difensori. Dopo anni passati ad osservare e analizzare compromissioni reali, è arrivato il momento di realizzare quella che riteniamo essere…

🔗 Link 👉 https://blog.8bitsecurity.com/2026/01/20/threat-hunting-su-cobalt-strike-dalle-viscere-del-beaconing-allinfrastruttura-c2/
#cybersecurity #infosec

Today’s Daily Term is online.

Can you guess the cybersecurity word of the day with 6 attempts 👀?

⬜️⬜️🟩⬜️⬜️
🟩🟩🟩🟩🟩

👉 https://8bitsecurity.com/daily-term/