AI Threat Alert
Paper 2510.14312v1
Terrarium: Revisiting the Blackboard for Multi-Agent Safety, Privacy, and Security Studies
multi-agent system (MAS) powered by large language models (LLMs) can automate tedious user tasks such as meeting scheduling that requires inter-agent collaboration. LLMs enable nuanced protocols that account
medium relevance
defense
Paper 2510.13322v1
Injection, Attack and Erasure: Revocable Backdoor Attacks via Machine Unlearning
networks (DNNs) due to their stealth and durability. While recent research has explored leveraging model unlearning mechanisms to enhance backdoor concealment, existing attack strategies still leave persistent traces that
high relevance
attack
Paper 2509.22040v1
"Your AI, My Shell": Demystifying Prompt Injection Attacks on Agentic AI Coding Editors
Agentic AI coding editors driven by large language models have recently become more popular due to their ability to improve developer productivity during software development. Modern editors such as Cursor
high relevance
attack
Previous
Page 16 of 16