Rafay Baloch

In this eye-opening talk, renowned ethical hacker and security researcher Baloch delves into the rapidly evolving world of cyber security, highlighting the potential threats and challenges posed by advanced technologies such as generative AI, deepfakes, and machine learning poisoning.

As cybercriminals become more sophisticated, leveraging cutting-edge tools to perpetrate increasingly complex attacks, it is crucial for businesses, governments, and individuals to stay one step ahead of the game and be prepared for the unforeseen.

Baloch will begin by providing an overview of generative AI and its potential implications on cybersecurity, discussing how adversarial machine learning techniques can be used to deceive or manipulate AI systems, leading to an entirely new category of cyber threats. He will then explore the growing phenomenon of deepfakes, examining the ethical concerns and security risks surrounding the creation and dissemination of convincing yet fabricated media content.

The talk will also touch upon the emerging issue of machine learning poisoning, where attackers manipulate training data to compromise machine learning models, causing them to make incorrect predictions or decisions. Baloch will provide insights on how to detect and defend against such attacks, ensuring the integrity of AI systems.