Artificial Intelligence

AI Security

Investigate how AI systems, including large language models (LLMs) and advanced multi-agent frameworks, fail under various conditions. Examine their susceptibility to input variations, adversarial attacks, or unexpected user manipulations. Explore whether input screening mechanisms in AI agent software effectively mitigate these vulnerabilities. Design experiments that stress-test these systems in diverse scenarios, revealing weak points that may compromise reliability or safety. Students will analyze patterns in failures and propose robust solutions to enhance system resilience.

Preventing Malicious Behavior in Future AI Systems

Envision scenarios where AI systems are connected to computer software, experimental devices, or autonomous processes with significant real-world impact. Evaluate how these systems might misuse their capabilities, such as creating harmful substances or bypassing safety constraints. Develop and test protocols that detect and prevent malicious actions, including frameworks for ethical safeguards, robust access control, and anomaly detection in AI behavior. Students will assess the balance between enabling AI autonomy and maintaining strict safety boundaries.

Designing Future-Proof Testing Protocols

Create comprehensive testing protocols that anticipate the misuse of AI systems in increasingly powerful and interconnected environments. Focus on ensuring that protocols address extreme yet plausible risks, including those involving experimental applications like drug development or autonomous decision-making. The protocols should incorporate ethical oversight, predictive failure analysis, and system-level audits to identify and mitigate potential dangers. Students will contribute innovative methodologies for securing the integrity of future AI systems.

Requirements

• Strong foundation in at least one of the following:
• Machine learning and AI
• Programming
• Statistics
• Ability to combine technical skills with creative thinking
• Interest in developing novel AI methods
• Desire to contribute to the future of transformative AI technologies

• Apply Today

AI Multi-agents

Investigate how large language models (LLMs) can collaborate as multi-agent systems to tackle intricate tasks, such as autonomously coding and logically reasoning through multifaceted processes. Explore the coordination of agents, role assignment, and dynamic task distribution to maximize efficiency. Evaluate the scalability and adaptability of these systems in increasingly complex scenarios. Students will aim to design and test innovative frameworks for agent collaboration, ensuring a seamless and robust performance that pushes the boundaries of current AI capabilities.

Requirements

• Strong foundation in at least one of the following:
• Machine learning and AI
• Programming
• Statistics
• Ability to combine technical skills with creative thinking
• Interest in developing novel AI methods
• Desire to contribute to the future of transformative AI technologies

• Apply Today

Deep Learning Applications

Explore cutting-edge methodologies to advance the performance, adaptability, and reliability of deep learning models, focusing on innovative techniques like curriculum learning, dataset distillation, and self-supervised learning. Investigate how these approaches enhance model efficiency and robustness while addressing key challenges such as overfitting, scalability, and generalization.

Requirements

For students proficient in conventional deep learning, this project offers the opportunity to explore unconventional and creative uses of deep learning models. Participants are encouraged to innovate by applying these models to novel domains or reimagining traditional applications. By pushing the boundaries of what deep learning can achieve, students will contribute to expanding its impact across diverse fields.

• Apply Today