Adversarial Machine Learning Researcher

Adversarial Machine Learning Researcher

Remote within the US

ABOUT THE ROLE:

HiddenLayer is entering an exciting new chapter in our company history and we are seeking a highly motivated and skilled Adversarial Machine Learning Researcher to join our research team. This role is focused on exploring and developing new techniques to improve the robustness, security, and interpretability of machine learning models against adversarial attacks. The ideal candidate will have a strong background in machine learning, deep learning, and cybersecurity, with a passion for advancing the field through innovative research.

WHO WE ARE:

HiddenLayer protects the world’s most valuable technologies from adversarial AI attacks. We were founded by AI professionals and security specialists with first-hand experience of how insidious adversarial AI attacks can be to detect and defend against. Determined to prove that these attacks were preventable, the team developed a unique, patent-pending, productized solution to support organizations in accelerating their adoption of AI securely. 

Our dedication to innovation has been recognized by prestigious awards such as RSA's Innovation Sandbox Winner, CB Insights AI 100, CyberTech 100, and SC's Most Promising Early-Stage Start-up.

WHAT YOU’LL DO:

• Research and Development

  • Adversarial Attack and Defense Techniques: Design, develop, and evaluate novel adversarial attack methods and defense mechanisms to improve the security and robustness of machine learning models.
  • Algorithm Innovation: Conduct research to propose new algorithms or improve existing ones to enhance model performance in adversarial settings.
  • Publication and Dissemination: Publish research findings in top-tier conferences and journals in the fields of machine learning, artificial intelligence, and cybersecurity.

• Collaboration and Communication

  • Cross-functional Collaboration: Work closely with data scientists, machine learning engineers, and cybersecurity experts to integrate adversarial robustness into deployed models and systems.
  • Knowledge Sharing: Contribute to internal knowledge-sharing sessions, seminars, and discussions, fostering a culture of learning and innovation within the team.
  • Client and Stakeholder Interaction: Collaborate with external partners, clients, and stakeholders to understand their needs and deliver tailored adversarial ML solutions.

• Model Testing and Evaluation

  • Vulnerability Assessment: Conduct thorough evaluations of existing machine learning models to identify vulnerabilities to adversarial attacks and recommend improvements.
  • Benchmarking: Develop and implement benchmarking frameworks to assess the effectiveness of adversarial attacks and defenses across various machine learning models and datasets.

• Tool Development

  • Prototype Development: Develop and maintain tools, libraries, and frameworks for generating adversarial examples, testing model robustness, and deploying defense strategies.
  • Automation: Automate the testing and evaluation processes to streamline the integration of adversarial robustness into the machine learning pipeline.

• Staying Current

  • Literature Review: Stay up-to-date with the latest advancements in adversarial machine learning, deep learning, and cybersecurity by continuously reviewing relevant academic literature and industry developments.
  • Continuous Learning: Attend conferences, workshops, and seminars to deepen knowledge in the field and apply learnings to ongoing research projects.

WHO YOU ARE:

• Ph.D. or Master’s degree in Computer Science, Machine Learning, Artificial Intelligence, Cybersecurity, or a related field.
• 2-5 years of experience in adversarial machine learning, cybersecurity, or a related research area.
• Proficiency in machine learning frameworks (e.g., TensorFlow, PyTorch).
• Strong programming skills in Python, with experience in developing machine learning models.
• Deep understanding of deep learning architectures (e.g., CNNs, RNNs, GANs) and their vulnerabilities.
• Knowledge of adversarial attack techniques (e.g., FGSM, PGD, DeepFool) and defense strategies (e.g., adversarial training, robust optimization).
• Strong publication record in top-tier conferences or journals in relevant fields.
• Excellent analytical a