Various approaches to LLM red-teaming leverage an attacker LLM to discover jailbreaks against a target.Several of them task attacker with formulating its own strategies to transform harmful queries into jailbreaks through trial and error, resulting in a semantically limited range of successful attacks.Another recent approach discovers diverse attacks by combining crowdsourced queries and tactics within the attacker's instructions, but does so at random, limiting effectiveness.This article introduces a novel framework, ADAPTIVE INSTRUCTION COM-POSITION, that combines crowdsourced texts according to an adaptive mechanism trained to jointly optimize attack effectiveness with diversity.We use reinforcement learning to balance exploration with exploitation in a combinatorial space of instructions to guide the attacker toward diverse generations tailored to target vulnerabilities.We show that our strategy substantially outperforms random combination on a set of effectiveness and diversity metrics, even under model transfer.Further, we show that it surpasses a host of recent adaptive approaches on the public benchmark Harmbench.We employ a lightweight neural contextual bandit that adapts to contrastively pretrained embeddings, and provide ablations to suggest that the contrastive property enables the network to generalize and scale to the massive space.Warning: this article discusses malicious content and methods for generating it using LLMs.

This paper introduces an innovative approach for cooperative vehicle platooning, integrating LiDAR-guided navigation, shared waypoints, and adaptive cruise control to optimize trajectory following and return maneuvers. Utilizing a pre-defined high-definition (HD) LiDAR map of the route, each vehicle in the platoon receives shared waypoints and utilizes onboard LiDAR sensors to localize itself relative to these waypoints. An adaptive cruise control system, guided by localized position and desired speed, regulates each vehicle's movement to ensure safe following distances and adherence to the planned trajectory. The results demonstrate the effectiveness of this approach in achieving precise trajectory following, maintaining optimal inter-vehicle spacing, and adapting safe velocity and heading according to the trajectory, thereby enabling coordinated platooning. This paper presents an autonomous platooning system for cooperative driving, showcasing the integration of advanced LiDAR-based technologies and control mechanisms.

As the automotive industry transitions towards autonomy, the need for advanced software-driven solutions becomes paramount. Software-defined autonomous vehicles (SDAVs) or SDVs represent a trans-formative shift in the automotive industry, promising enhanced safety, efficiency, and flexibility. It has the potential to save thousands of lives by reducing the human error. Therefore, the research explores the crucial design considerations and framework necessary for the development and deployment of SDVs. Additionally, the study examines the foundational concepts and the intricate relationship between hardware and software architecture. Moreover, a dynamic invehicle infotainment (IVI) system has been developed to deliver real-time sensor notifications and warnings, enhancing overall safety. The functionality and effectiveness of a personalized IVI have been assessed at the TiHAN testbed in IIT Hyderabad. The developed software-defined vehicle and IVI system possess connectivity capabilities enabling interaction with the environment and other vehicles, thereby reinforcing accident prevention measures.