Dario Pasquini, Evgenios M. Kornaropoulos, Giuseppe Ateniese · ACM Workshop on Artificial Intelligence and Security (AISec) 2026 · 2026
DOI: 10.1145/3847352.3848083
Counts differ because each database indexes a different set of publications. We treat OpenAlex as the canonical count; Google Scholar is not shown (no API, and crawling it violates its ToS).
Large language models (LLMs) are making multi-step cyberattacks cheaper to run and easier to automate. We present Mantis, a mechanism that leverages prompt injection for defensive purposes, turning it against the attacking LLM-agent itself. Once Mantis detects an attacking agent, it injects defender-crafted content into system responses and steers the agent toward one of two outcomes: a tarpit that wastes time and resources, or a controlled hack-back action that helps collect attribution information. Mantis combines decoy services with dynamic prompt injections and uses the attacker’s own interaction loop to deliver the defense. In our evaluation, Mantis achieves the sabotage objective in 95.4% of runs and keeps attacker success below 3%. We release Mantis as open source.
Last synced
ACM SIGSAC Conference on Computer and Communications Security (CCS) 2026 · 0 citations
No comments yet — start the discussion below.