The field of artificial intelligence and autonomous systems is rapidly evolving, with a growing focus on security and safety. Recent research has highlighted the importance of addressing security vulnerabilities in AI models and autonomous systems, such as unmanned aerial vehicles (UAVs) and large language models (LLMs). One of the key directions in this area is the development of novel security protocols and mechanisms to prevent malicious attacks and ensure the secure operation of these systems. Another area of research is the characterization of cyber attacks against critical infrastructures, such as space infrastructures, and the development of frameworks to analyze and mitigate these threats. Noteworthy papers in this area include: An Empirical Study on the Security Vulnerabilities of GPTs, which presents a comprehensive analysis of security vulnerabilities in large language models. Characterizing Cyber Attacks against Space Infrastructures with Missing Data proposes a framework to characterize cyber attacks against space infrastructures and extrapolate missing data to reconstruct attack scenarios. Systems Security Foundations for Agentic Computing articulates research problems in AI agent security and privacy, emphasizing the need for an end-to-end security approach. Password-Activated Shutdown Protocols for Misaligned Frontier Agents introduces a novel mechanism for emergency shutdown of misaligned AI agents, contributing to the development of more secure and reliable AI systems. Unfolding Challenges in Securing and Regulating Unmanned Air Vehicles provides a comprehensive analysis of security challenges in UAVs and highlights the need for regulatory frameworks to ensure secure and regulated UAV networks. WildCode: An Empirical Analysis of Code Generated by ChatGPT, which investigates the quality and security of code generated by large language models, highlighting the need for improved security measures in AI-generated code.