4 papers
Beware of Agentic Botnets: Scalable Untargeted Promptware Attacks via Universal and Transferable Adversarial HalluSquatting
Aya Spira, Stav Cohen, Elad Feldman +3
The growing adoption of agentic LLM applications has introduced a new threat previously named as promptware. While prior work has established that adversaries can exploit direct ch…
The Promptware Kill Chain: How Prompt Injections Gradually Evolved Into a Multistep Malware Delivery Mechanism
Oleg Brodt, Elad Feldman, Bruce Schneier +1
Prompt injection was initially framed as the large language model (LLM) analogue of SQL injection. However, over the past three years, attacks labeled as prompt injection have evol…
Invitation Is All You Need! Promptware Attacks Against LLM-Powered Assistants in Production Are Practical and Dangerous
Ben Nassi, Stav Cohen, Or Yair
The growing integration of LLMs into applications has introduced new security risks, notably known as Promptware - maliciously engineered prompts designed to manipulate LLMs to com…
Here Comes The AI Worm: Unleashing Zero-click Worms that Target GenAI-Powered Applications
Stav Cohen, Ron Bitton, Ben Nassi
In this paper, we show that when the communication between GenAI-powered applications relies on RAG-based inference, an attacker can initiate a computer worm-like chain reaction th…