#AIOps
#MLSecOps
#Automotive_Security
"FuncPoison: Poisoning Function Library to Hijack Multi-agent Autonomous Driving Systems", 2025.
// FuncPoison - new poisoning-based attack targeting the function library to manipulate the behavior of LLM-driven multi-agent autonomous systems. FuncPoison manipulates one agent's decisions-such as misinterpreting road conditions-triggering cascading errors that mislead other agents in the system
See also:
]-> Awesome Data Poisoning and Backdoor Attacks
Post #1621
157