Inside the LLM | Understanding AI & the Mechanics of Modern Attacks
Learn how attackers exploit tokenization, embeddings and LLM attention mechanisms to bypass LLM security filters and hijack model behavior.
Learn how attackers exploit tokenization, embeddings and LLM attention mechanisms to bypass LLM security filters and hijack model behavior.
LLMs make competent ransomware crews faster and novices more dangerous. The risk is not superintelligent malware, but rather industrialized extortion.
Read how two Cisco Network Academy Cup winners went from students to operators behind Salt Typhoon, a global cyber espionage campaign targeting telecoms.
Mei Danowski & Eugenio Benincasa unpack how Chinese firms running attack-defense exercises fuel state-linked offensive cyber operations.
Accelerate adversary tracking and reveal hidden infrastructure with our open-source Synapse Rapid Power-Up for Validin.
Learn how to detect malware that generates code at runtime. SentinelLABS reveals hunting techniques and how to uncover novel AI-enabled threats.
SentinelLABS uncovers a coordinated spearphishing campaign targeting organizations critical to Ukraine's war relief efforts.
AI agents promise speed, but at what cost to trust? Dreadnode’s Wendiggensen & Palm unpack this dilemma through a hands-on study of leaked Russian data.
LLM-enabled malware poses new challenges for detection. SentinelLABS presents groundbreaking research on how to hunt for this new class of threats.
DPRK-aligned threat actors abuse CTI platforms to detect infrastructure exposure and scout for new assets.
Crypto scammers use fake YouTube bots, AI videos, and obfuscated smart contracts to steal $900K+, targeting unwary traders.