University of Cambridge > Talks.cam > Machine Learning Reading Group @ CUED > Defending Against Adversarial Attacks

  Browse A-Z

Log in

University Account External (via Google)

🔐 Log In

Information on

Subscribing to talksdetails Finding a talkdetails Adding a talkdetails Disseminating talksdetails Help and Documentationdetails

ℹī¸ Information

Defending Against Adversarial Attacks

Download to your calendar using vCal

If you have a question about this talk, please contact .

Adversarial examples are inputs which have been maliciously perturbed to induce inappropriate responses from a machine learning system, but which are generally indistinguishable from innocent inputs by humans. They thus represent a substantial threat to the reliability and practicability of ML applications, as systems vulnerable to manipulation in this way cannot be trusted with important decisions. Despite this, surprisingly little is understood about the mechanisms by which adversarial examples arise, and how we might construct systems which are resilient to attack by these samples. We chart the evolution of the literature on adversarial attacks by considering some initially proposed explanations for how they arise. We discuss some defence mechanisms such as adversarial training and the less obvious approach of network distillation. We then briefly summarise the current state of the field.

This talk is part of the Machine Learning Reading Group @ CUED series.

This talk is included in these lists:

Note that ex-directory lists are not shown.

Other lists

Average on weekdays: 9059.58551618 kWh Churchill College, University of Cambridge Online ONLY: https://zoom.us/j/93882601826?pwd=dEMzYTNUSkFGZ2ttMHVYT3dLdjZRUT09 Meeting ID: 938 8260 1826 Passcode: hLg0x6Hvu8

Other talks

Together Now: Cooperation and Collaboration in Social Art Practice Emergency Medicine and Metabolic Medicine Online Causal Inference Seminar CSAR lecture: In a post-Ozempic world, have we cured obesity? Title to be confirmed Talk TBC
 

Š 2006-2025 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity