A General Framework for Defending Against Backdoor Attacks via Influence Graph

Abstract

In this work, we propose a new and general framework to defend against backdoor attacks, inspired by the fact that attack triggers usually follow a SPECIFIC type of attacking pattern, and therefore, poisoned training examples have greater impacts on each other during training. We introduce the notion of the influence graph, which consists of nodes and edges respectively representative of individual training points and associated pair-wise influences. The influence between a pair of training points represents the impact of removing one training point on the prediction of another, approximated by the influence function (Koh & Liang, 2017). Malicious training points are extracted by finding the maximum average sub-graph subject to a particular size. Extensive experiments on computer vision and natural language processing tasks demonstrate the effectiveness and generality of the proposed framework.

IMBERT: Making BERT Immune to Insertion-based Backdoor Attacks

“…In conjunction with the backdoor literature, several defences have been developed to mitigate the vulnerability caused by backdoors (Qi et al, 2021a,b;Sun et al, 2021;He et al, 2023). Depending on the access to the training data, defensive approaches can be categorised into two types: ( 1 Previous works have empirically demonstrated that for multiple NLP tasks, the attention scores attained from the self-attention module can provide plausible and meaningful interpretations of the model's prediction w.r.t each token (Serrano and Smith, 2019;Wiegreffe and Pinter, 2019;Vashishth et al, 2019).…”

CATER: Intellectual Property Protection on Text Generation APIs via Conditional Watermarks

“…Qi et al [33] have shown that GPT2 can effectively identify trigger words targeting the corruption of text classifications. It has been demonstrated that one can use influence graphs as a means of the remedy for data poisoning on various NLP tasks [41] 3 CATER…”