The existing approaches to instruction trace-based security monitoring hardware are dependent on the privileged software, which presents a significant challenge in defending against attacks on privileged software itself. To address this challenge, we propose Interstellar, which introduces a partitioned hardware near the CPU's main core and leverages the benefit of hardware-level security monitoring. Interstellar is fully partitioned, parallelized, and simultaneously detecting security monitoring hardware. Interstellar's design makes malicious software hard to reverse-engineer how Interstellar detects the attacks, and Interstellar efficiently protects the system against the attacks on the privileged software(e.g., Trusted Execution Environment (TEE)). Moreover, Interstellar not only monitors but also blocks various attacks in a timely manner without stalling a CPU core by designing with a finite-state machine.

Hyungjoo Chae, Taeyoon Kwon, Seungjun Moon, Yongho Song, Dongjin Kang, Kai Tzu-iunn Ong, Beong-woo Kwak, Seonghyeon Bae, Seung-won Hwang, Jinyoung Yeo. Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing. 2024.

Hyungjoo Chae, Yongho Song, Kai Ong, Taeyoon Kwon, Minjin Kim, Youngjae Yu, Dongha Lee, Dongyeop Kang, Jinyoung Yeo. Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing. 2023.

To build open-domain chatbots that are able to use diverse communicative skills, we propose a novel framework BOTSTALK, where multiple agents grounded to the specific target skills participate in a conversation to automatically annotate multi-skill dialogues.We further present Blended Skill BotsTalk (BSBT), a large-scale multi-skill dialogue dataset comprising 300K conversations.Through extensive experiments, we demonstrate that our dataset can be effective for multi-skill dialogue systems which require an understanding of skill blending as well as skill grounding.Our code and data are available at https://github. com/convei-lab/BotsTalk.