# PECAN: A Deterministic Certified Defense Against Backdoor Attacks

Source: [PECAN: A Deterministic Certified Defense Against Backdoor Attacks](<https://www.sota2.com/research/paper/68fa73421e209131cea5b5a5>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T02:45:17.730Z

Authors: Yuhao Zhang, Aws Albarghouthi, Loris D'Antoni

Published: 2023-01-27T16:25:43.000Z

## Abstract

Neural networks are vulnerable to backdoor poisoning attacks, where the attackers maliciously poison the training set and insert triggers into the test input to change the prediction of the victim model. Existing defenses for backdoor attacks either provide no formal guarantees or come with expensive-to-compute and ineffective probabilistic guarantees. We present PECAN, an efficient and certified approach for defending against backdoor attacks. The key insight powering PECAN is to apply off-the-shelf test-time evasion certification techniques on a set of neural networks trained on disjoint partitions of the data. We evaluate PECAN on image classification and malware detection datasets. Our results demonstrate that PECAN can (1) significantly outperform the state-of-the-art certified backdoor defense, both in defense strength and efficiency, and (2) on real back-door attacks, PECAN can reduce attack success rate by order of magnitude when compared to a range of baselines from the literature.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2301.11824>)

[PDF](<https://arxiv.org/pdf/2301.11824.pdf>)
