Machine Learning Attacks – A New Era of Security Epidemic


3rd December 2020
Speaker Date: 3rd December 2020
Speaker Time: IST: 16:30-17:30
Attendee Date: 3rd December 2020
Attendee Time: IST: 16:30-17:30 | SGT: 19:00-20:00 | AEST: 22:00-23:00
Duration: 25 mins
Ashima Purohit
Engineering Manager, PayPal

Machine learning is increasingly being used at the core of several critical applications, such as for self-driving cars, drug recommendation systems, high-volume trading algorithms, privacy and security of sensitive data, etc; any adversarial manipulation on an ML model can lead to devastating results.

Wondering what would it be like to have your machine learning (ML) model come under security attack? Have you thought through how to monitor security attacks on your AI/ML models? Historically less attention has been paid to the ways in which AI can be used maliciously. ML models, much like any piece of software, are prone to theft and subsequent reverse-engineering. Machine learning is susceptible to adversarial activity, where an attacker can manipulate the input data to deceive the deployed ML model.

Join us to experience the research and solutions we developed to combat the ML threat. This session aims to describe the potential threats associated with current methods of collecting or building ML systems and elaborate on the techniques to protect these models. The intention is to bridge the gap between machine learning and privacy and security technologies by helping attendees get acquainted with machine learning, the potential threats to privacy, the proposed solutions, and the challenges that lie ahead.

You may also be interested in

26th, November

Time
Beyond Managing Your Manager

The deep-dive presents why conflicts with your manager are inevitable based on differences in priorities and perspectives, and how to...

26th, November

Time
Top 10 Algorithms for Coding Interviews

So we are all the best coders, but have you see the run time of the code you are writing?...

3rd, September

Time
Imposter Syndrome: Overcoming Self-Doubt in Success

Impostor Syndrome is the domain of the high achiever. Those who set the bar low are rarely it’s victim. What...

26th, November

Time
Mental Bookmarks and the Fractal Nature of Success

Good discussions are supposed to diverge from their intended path. Free association is a feature, not a bug, and helps...

26th, November

Time
Slowdown to Gain Speed: Technical practices that take time but save time

As a software development manager or a technical leader you are eager to remove impediments so your team can produce...

3rd, September

Time
Design Principles for the Effective Developer

How many design patterns and principles can you name as developer? Are they important? Should we not rather focus on...