REVIEW 2 cited by
Backdoor attacks and defenses in feature-partitioned collaborative learning
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Since there are multiple parties in collaborative learning, malicious parties might manipulate the learning process for their own purposes through backdoor attacks. However, most of existing works only consider the federated learning scenario where data are partitioned by samples. The feature-partitioned learning can be another important scenario since in many real world applications, features are often distributed across different parties. Attacks and defenses in such scenario are especially challenging when the attackers have no labels and the defenders are not able to access the data and model parameters of other participants. In this paper, we show that even parties with no access to labels can successfully inject backdoor attacks, achieving high accuracy on both main and backdoor tasks. Next, we introduce several defense techniques, demonstrating that the backdoor can be successfully blocked by a combination of these techniques without hurting main task accuracy. To the best of our knowledge, this is the first systematical study to deal with backdoor attacks in the feature-partitioned collaborative learning framework.
Forward citations
Cited by 2 Pith papers
-
Exploiting Edge Features for Transferable Adversarial Attacks in Distributed Machine Learning
Intercepting intermediate features in split neural network inference lets black-box attackers build surrogate models whose adversarial examples transfer to the target far more often, e.g., 96% versus 61% success in on...
-
A Survey on Data Security in Large Language Models
A survey of data security risks in LLMs that organizes threats, defenses, and evaluation datasets, with notable factual errors in its tables.
Discussion (0). Sign in to comment.