SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2302.04116 · 2023

Training-free Lexical Backdoor Attacks on Language Models

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Large-scale language models have achieved tremendous success across various natural language processing (NLP) applications. Nevertheless, language models are vulnerable to backdoor attacks, which inject stealthy triggers into models for steering them to undesirable behaviors. Most existing backdoor attacks, such as data poisoning, require further (re)training or fine-tuning language models to learn the intended backdoor patterns. The additional training process however diminishes the stealthiness of the attacks, as training a language model usually requires long optimization time, a massive amount of data, and considerable modifications to the model parameters. In this work, we propose Training-Free Lexical Backdoor Attack (TFLexAttack) as the first training-free backdoor attack on language models. Our attack is achieved by injecting lexical triggers into the tokenizer of a language model via manipulating its embedding dictionary using carefully designed rules. These rules are explainable to human developers which inspires attacks from a wider range of hackers. The sparse manipulation of the dictionary also habilitates the stealthiness of our attack. We conduct extensive experiments on three dominant NLP tasks based on nine language models to demonstrate the effectiveness and universality of our attack. The code of this work is available at https://github.com/Jinxhy/TFLexAttack.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2302.04116")
get_code_for_paper("2302.04116")
have("2302.04116")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2302.04116.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2302.04116.svg)](https://syntology.ai/paper/2302.04116)

Connect an agent — have() is free.