ARS Session 05 - Likhitha Lakshmi Gudivada
Security Risks and Guardrails in Large Language Models: A Practical Analysis of LLM Vulnerabilities and Safety Mechanisms Description:This project focuses on improving the security, safety, and reliability of Large Language Models (LLMs) by implementing guardrail-based protection mechanisms. The project examines major LLM vulnerabilities such as prompt injection attacks, hallucinations, unsafe content generation, and sensitive data leakage, which can impact the trustworthiness of AI systems in real-world applications. A secure LLM workflow prototype was developed using AWS cloud services including Amazon API Gateway, AWS Lambda, Amazon Bedrock, Bedrock Guardrails, AWS CloudWatch, and AWS CDK. The system performs input validation, content filtering, risk classification, output moderation, and logging/monitoring to detect and reduce unsafe interactions before responses are returned to users. The overall goal is to demonstrate practical security mechanisms that can support safer deployment of AI-powered applications in cloud environments.

ARS Session 06 - Mingsorn Siraphat

The Strange Math That Predicts (Almost) Anything

기업이 꼭 알아야 할 '온톨로지'의 모든 것 (김학래 중앙대 교수)

ARS Session 12 - Hannah Lee

MBAHCHM - MMH019 - Emerging Issues in Health Care Management - Block-2 | IGNOU RC Delhi-2

The FULL VIDEO of Trump they didn’t want released

ARS Session 03 - Namrata Vijay Mali

How AI agents & Claude skills work (Clearly Explained)

Which country has the best education in the world? - The Global Story podcast, BBC World Service

Microsoft Build 2026 | Satya Nadella Opening Keynote

ARS Session 03 - Peini Wu

RL for Agents Workshop - Deep Dive on Training Agents with RL and Open Source

How Gen AI is reshaping video production with Adobe | The Data Movement

How To Think SO CLEARLY People Assume You're A Genius

AI 최후의 승자 이래서 구글입니다 (KAIST 전자및전기공학부 김정호 교수)

ARS Session 13 - Vidhya Lakshmi Amarnath

RAG & MCP Fundamentals – A Hands-On Crash Course

ARS Session 10 - Arlena Collins

ARS Session 05 - David Hiltzmen

