Adversarial and Poisoning Attacks against Speech Systems: Where to Find Them?

In this presentation, we delve into the intricate world of machine learning system vulnerabilities, focusing primarily on poisoning attacks and their impact on data integrity. The speaker, research scientist Thomas Thebuad, offers a comprehensive breakdown of how data can be maliciously altered to affect machine learning outcomes, highlighting the dangers and effectiveness of both "dirty labels" and "clean label" poisoning. The talk further explores adversarial attacks, illustrating how subtle manipulations can deceive machine learning models into incorrect predictions.
This video serves as an introduction to the complex interactions between training data and system performance, emphasizing the importance of trust in data integrity. With real-world examples and theoretical insights, the speaker sheds light on various attack strategies, defense mechanisms, and the ongoing battle between system security and adversarial tactics.
Whether you're a cybersecurity expert, a machine learning enthusiast, or simply curious about the ethical implications of AI, this presentation will equip you with a deeper understanding of the challenges and necessary precautions in developing robust machine learning systems.