Attack of the Tails: Yes, you Really can Backdoor Federated Learning
From Google TechTalks · 16:15
Show by Google TechTalks
A Google TechTalk, 2020/7/30, presented by Dimitris Papailiopoulos, University of Wisconsin-MadisonABSTRACT: Due to its decentralized nature, Federated Learning (FL) lends itself to adversarial attacks in the form of backdoors during training. A range of FL backdoor attacks have been introduced in the literature, but also methods to defend against them, and it is currently an open question whether FL systems can be tailored to be robust against backdoors. In this work, we provide evidence to the contrary. We first establish that robustness to backdoors implies model robustness to adversarial examples, a major open problem in itself. Furthermore, detecting the presence of a backdoor in a FL model is unlikely assuming first order oracles or polynomial time. We couple our theoretical results with a new family of backdoor attacks, which we refer to as edge-case backdoors. An edge-case backdoor forces a model to misclassify on seemingly easy inputs that are however unlikely to be part of the training, or test data, i.e., they live on the tail of the input distribution. We explain how these edge-case backdoors can lead to unsavory failures and may have serious repercussions on fairness, and exhibit that with careful tuning at the side of the adversary, one can insert them across a range of machine learning tasks (e.g., image classification, OCR, text prediction, sentiment analysis).Uploaded 04-06-21
More episodes of Google TechTalks
More episodes
- Threat Models for Memorization: Privacy, Copyright, and Everything In-Between
- Technology Assisted Reading Acquisition: Children Acquiring Literacy Naturally
- sex on the internet, the realities of porn, sexual privacy,
- Privacy Auditing of Large Language Models
- The Limits and Possibilities of One Run Auditing
- PhotoTechEDU Day 29: Photographing VR Panoramas
- Privacy Ripple Effects from Adding or Removing Personal Information in Language Model Training
- Inside VMware Fusion
- Java Posse Episode 100 (Live Special)
- Cascading Adversarial Bias from Injection to Distillation in Language Models
PodSearch is a free, independent podcast search engine. Read about PodSearch, the privacy policy or contact us.