Instruction Backdoor Attacks Against Customized LLMs
The increasing demand for customized Large Language Models (LLMs) has led to the development of solutions like GPTs. These solutions facilitate tailored LLM creation via natural language prompts without coding. However, the trustworthiness of third-party custom versions of LLMs remains an essential concern. In this paper, we propose the first instruction backdoor attacks against applications integrated with untrusted customized LLMs (e.g., GPTs). Specifically, these attacks embed the backdoor into the custom version of LLMs by designing prompts with backdoor instructions, outputting the attacker's desired result when inputs contain the pre-defined triggers. Our attack includes 3 levels of attacks: word-level, syntax-level, and semantic-level, which adopt different types of triggers with progressive stealthiness. We stress that our attacks do not require fine-tuning or any modification to the backend LLMs, adhering strictly to GPTs development guidelines. We conduct extensive experiments on 6 prominent LLMs and 5 benchmark text classification datasets. The results show that our instruction backdoor attacks achieve the desired attack performance without compromising utility. Additionally, we propose two defense strategies and demonstrate their effectiveness in reducing such attacks. Our findings highlight the vulnerability and the potential risks of LLM customization such as GPTs.
Code (1)
Tasks
Language ModellingLarge Language Modeltext-classificationText ClassificationSimilar Papers 제목 키워드 기반
Merging Triggers, Breaking Backdoors: Defensive Poisoning for Instruction-Tuned Language Models
Large Language Models (LLMs) have greatly advanced Natural Language Processing (NLP), particularly through instruction tuning, which enables broad task generalization without additional fine-tuning. However, their relian…
Latent Instruction Representation Alignment: defending against jailbreaks, backdoors and undesired knowledge in LLMs
We address jailbreaks, backdoors, and unlearning for large language models (LLMs). Unlike prior work, which trains LLMs based on their actions when given malign instructions, our method specifically trains the model to c…
TuBA: Cross-Lingual Transferability of Backdoor Attacks in LLMs with Instruction Tuning
The implications of backdoor attacks on English-centric large language models (LLMs) have been widely examined - such attacks can be achieved by embedding malicious behaviors during training and activated under specific …
BEEAR: Embedding-based Adversarial Removal of Safety Backdoors in Instruction-tuned Language Models
Safety backdoor attacks in large language models (LLMs) enable the stealthy triggering of unsafe behaviors while evading detection during normal interactions. The high dimensionality of potential triggers in the token sp…
Code GenerationYour Agent Can Defend Itself against Backdoor Attacks
Despite their growing adoption across domains, large language model (LLM)-powered agents face significant security risks from backdoor attacks during training and fine-tuning. These compromised agents can subsequently be…
Large Language Model