Adversarial Neuron Pruning Purifies Backdoored Deep Models
Dec 6, 2021
Speakers
Dongxian Wu
Speaker · 0 followers
About
As deep neural networks (DNNs) are growing larger, their requirements for computational resources become huge, which makes outsourcing training more popular. Training in a third-party platform, however, may introduce potential risks that a malicious trainer will return backdoored DNNs, which behave normally on clean samples but output targeted misclassifications whenever a trigger appears at the test time. Without any knowledge of the trigger, it is difficult to distinguish or recover benign DNNs from backdoored ones. In this paper, we first identify an unexpected sensitivity of backdoored DNNs, that is, they are much easier to collapse and tend to predict the target label on clean samples when their neurons are adversarially perturbed. Based on these observations, we propose a novel model repairing method, termed Adversarial Neuron Pruning (ANP), which prunes some sensitive neurons to purify the injected backdoor. Experiments show, even with only an extremely small amount of clean data (e.g., 1As deep neural networks (DNNs) are growing larger, their requirements for computational resources become huge, which makes outsourcing training more popular. Training in a third-party platform, however, may introduce potential risks that a malicious trainer will return backdoored DNNs, which behave normally on clean samples but output targeted misclassifications whenever a trigger appears at the test time. Without any knowledge of the trigger, it is difficult to distinguish or recover benign DNN…
Organizer
NeurIPS 2021
Account · 1.9k followers
About NeurIPS 2021
Neural Information Processing Systems (NeurIPS) is a multi-track machine learning and computational neuroscience conference that includes invited talks, demonstrations, symposia and oral and poster presentations of refereed papers. Following the conference, there are workshops which provide a less formal setting.
Like the format? Trust SlidesLive to capture your next event!
Professional recording and live streaming, delivered globally.
Sharing
Recommended Videos
Presentations on similar topic, category or speaker
Fast Routing under Uncertainty: Adaptive Learning in Congestion Games via Exponential Weights
Watch later
Dong Quan Vu, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Near-Optimal No-Regret Learning in General Games
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
SurvITE: Learning Heterogeneous Treatment Effects from Time-to-event Data
Watch later
Alicia Curth, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Deep Reinforcement Learning
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
On the Sample Complexity of Privately Learning Axis-Aligned Rectangles
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Theorem-Aware Geometry Problem Solving with Symbolic Reasoning and Theorem Prediction
Watch later
Pan Lu, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%