Nura Kawa

Machine Learning: Promising, but Perilous

What if the pre-trained model you downloaded has a hidden backdoor? Learn how to protect your ML systems from these inherited, transferable attacks.

Machine Learning: Promising, but Perilous
#1about 5 minutes

The dual nature of machine learning's power

Machine learning's increasing power and accessibility, exemplified by complex tasks like panoptic segmentation, also introduces significant security vulnerabilities.

#2about 3 minutes

Accelerating development with transfer learning

Transfer learning allows developers to repurpose large pre-trained teacher models for specific tasks with minimal data and compute by fine-tuning a new student model.

#3about 2 minutes

How transfer learning's benefits create security risks

The core benefits of transfer learning, such as knowledge transfer and minimal training, directly create attack vectors for adversaries.

#4about 5 minutes

Exploring evasion and poisoning attacks in ML

Adversarial examples can fool models with subtle input changes (evasion), while poisoned data can insert hidden backdoors, with both risks amplified by transfer learning.

#5about 3 minutes

Integrating security with a pre-development risk assessment

Before writing code, perform a thorough risk assessment by defining security requirements, evaluating resource availability, and conducting threat modeling for your specific use case.

#6about 3 minutes

Selecting robust teacher models for secure transfer learning

Mitigate risks by choosing transparent and trustworthy teacher models and using robust models hardened through techniques like adversarial training.

#7about 1 minute

Fortifying student models to prevent transferred attacks

Strengthen your student model by fine-tuning all layers to diverge from the teacher model, using backdoor detection, and performing continuous stress testing.

#8about 2 minutes

Key resources for developing secure ML systems

Practical resources like the Adversarial Robustness Toolbox for developers and security principles from the National Cybersecurity Center can help you build more secure ML systems.

Related jobs
Jobs that call for the skills explored in this talk.

Featured Partners

Related Videos

See all videos
A hundred ways to wreck your AI - the (in)security of machine learning systems24:23

A hundred ways to wreck your AI - the (in)security of machine learning systems

Balázs Kiss

Hacking AI - how attackers impose their will on AI27:02

Hacking AI - how attackers impose their will on AI

Mirko Ross

What non-automotive Machine Learning projects can learn from automotive Machine Learning projects48:01

What non-automotive Machine Learning projects can learn from automotive Machine Learning projects

Jan Zawadzki

Beyond the Hype: Building Trustworthy and Reliable LLM Applications with Guardrails29:00

Beyond the Hype: Building Trustworthy and Reliable LLM Applications with Guardrails

Alex Soto

How AI Models Get Smarter35:16

How AI Models Get Smarter

Ankit Patel

Staying Safe in the AI Future27:26

Staying Safe in the AI Future

Cassie Kozyrkov

Prompt Injection, Poisoning & More: The Dark Side of LLMs23:24

Prompt Injection, Poisoning & More: The Dark Side of LLMs

Keno Dreßel

GenAI Security: Navigating the Unseen Iceberg24:33

GenAI Security: Navigating the Unseen Iceberg

Maish Saidel-Keesing

From learning to earning

Jobs that call for the skills explored in this talk.