Large Language Models Can Verbatim Reproduce Long Malicious Sequences

• URL: http://arxiv.org/abs/2503.17578v1
• Date: Fri, 21 Mar 2025 23:24:49 GMT
• Title: Large Language Models Can Verbatim Reproduce Long Malicious Sequences
• Authors: Sharon Lin, Krishnamurthy, Dvijotham, Jamie Hayes, Chongyang Shi, Ilia Shumailov, Shuang Song,
• Abstract summary: Backdoor attacks on machine learning models have been extensively studied.<n>This paper re-examines the concept of backdoor attacks in the context of Large Language Models.<n>We find that arbitrary responses containing hard coded keys of $leq100$ random characters can be reproduced when triggered by a target input.
• Score: 23.0516001201445
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Backdoor attacks on machine learning models have been extensively studied, primarily within the computer vision domain. Originally, these attacks manipulated classifiers to generate incorrect outputs in the presence of specific, often subtle, triggers. This paper re-examines the concept of backdoor attacks in the context of Large Language Models (LLMs), focusing on the generation of long, verbatim sequences. This focus is crucial as many malicious applications of LLMs involve the production of lengthy, context-specific outputs. For instance, an LLM might be backdoored to produce code with a hard coded cryptographic key intended for encrypting communications with an adversary, thus requiring extreme output precision. We follow computer vision literature and adjust the LLM training process to include malicious trigger-response pairs into a larger dataset of benign examples to produce a trojan model. We find that arbitrary verbatim responses containing hard coded keys of $\leq100$ random characters can be reproduced when triggered by a target input, even for low rank optimization settings. Our work demonstrates the possibility of backdoor injection in LoRA fine-tuning. Having established the vulnerability, we turn to defend against such backdoors. We perform experiments on Gemini Nano 1.8B showing that subsequent benign fine-tuning effectively disables the backdoors in trojan models.

Related papers

• When Backdoors Speak: Understanding LLM Backdoor Attacks Through Model-Generated Explanations [58.27927090394458]
  Large Language Models (LLMs) are known to be vulnerable to backdoor attacks.<n>In this paper, we examine backdoor attacks through the novel lens of natural language explanations.<n>Our results show that backdoored models produce coherent explanations for clean inputs but diverse and logically flawed explanations for poisoned data.
  arXiv  Detail & Related papers  (2024-11-19T18:11:36Z)
• DROJ: A Prompt-Driven Attack against Large Language Models [0.0]
  Large Language Models (LLMs) have demonstrated exceptional capabilities across various natural language processing tasks. Despite massive alignment efforts, LLMs remain susceptible to adversarial jailbreak attacks. We introduce a novel approach, Directed Rrepresentation Optimization Jailbreak (DROJ)
  arXiv  Detail & Related papers  (2024-11-14T01:48:08Z)
• SecAlign: Defending Against Prompt Injection with Preference Optimization [52.48001255555192]
  Adrial prompts can be injected into external data sources to override the system's intended instruction and execute a malicious instruction.<n>We propose a new defense called SecAlign based on the technique of preference optimization.<n>Our method reduces the success rates of various prompt injections to around 0%, even against attacks much more sophisticated than ones seen during training.
  arXiv  Detail & Related papers  (2024-10-07T19:34:35Z)
• MEGen: Generative Backdoor in Large Language Models via Model Editing [56.46183024683885]
  Large language models (LLMs) have demonstrated remarkable capabilities. Their powerful generative abilities enable flexible responses based on various queries or instructions. This paper proposes an editing-based generative backdoor, named MEGen, aiming to create a customized backdoor for NLP tasks with the least side effects.
  arXiv  Detail & Related papers  (2024-08-20T10:44:29Z)
• Human-Interpretable Adversarial Prompt Attack on Large Language Models with Situational Context [49.13497493053742]
  This research explores converting a nonsensical suffix attack into a sensible prompt via a situation-driven contextual re-writing. We combine an independent, meaningful adversarial insertion and situations derived from movies to check if this can trick an LLM. Our approach demonstrates that a successful situation-driven attack can be executed on both open-source and proprietary LLMs.
  arXiv  Detail & Related papers  (2024-07-19T19:47:26Z)
• Securing Multi-turn Conversational Language Models From Distributed Backdoor Triggers [29.554818890832887]
  Large language models (LLMs) have acquired the ability to handle longer context lengths and understand nuances in text. This paper exposes a vulnerability that leverages the multi-turn feature and strong learning ability of LLMs to harm the end-user. We propose a decoding time defense that scales linearly with assistant response sequence length and reduces the backdoor to as low as 0.35%.
  arXiv  Detail & Related papers  (2024-07-04T20:57:06Z)
• TrojanRAG: Retrieval-Augmented Generation Can Be Backdoor Driver in Large Language Models [16.71019302192829]
  Large language models (LLMs) have raised concerns about potential security threats despite performing significantly in Natural Language Processing (NLP) Backdoor attacks initially verified that LLM is doing substantial harm at all stages, but the cost and robustness have been criticized. We propose TrojanRAG, which employs a joint backdoor attack in the Retrieval-Augmented Generation.
  arXiv  Detail & Related papers  (2024-05-22T07:21:32Z)
• Simulate and Eliminate: Revoke Backdoors for Generative Large Language Models [42.19147076519423]
  generative large language models (LLMs) dominate various Natural Language Processing (NLP) tasks from understanding to reasoning. A malicious adversary may publish poisoned data online and conduct backdoor attacks on the victim LLMs pre-trained on the poisoned data. We present Simulate and Eliminate (SANDE) to erase the undesired backdoored mappings for generative LLMs.
  arXiv  Detail & Related papers  (2024-05-13T11:53:42Z)
• Coercing LLMs to do and reveal (almost) anything [80.8601180293558]
  It has been shown that adversarial attacks on large language models (LLMs) can "jailbreak" the model into making harmful statements. We argue that the spectrum of adversarial attacks on LLMs is much larger than merely jailbreaking.
  arXiv  Detail & Related papers  (2024-02-21T18:59:13Z)
• Backdoor Learning on Sequence to Sequence Models [94.23904400441957]
  In this paper, we study whether sequence-to-sequence (seq2seq) models are vulnerable to backdoor attacks. Specifically, we find by only injecting 0.2% samples of the dataset, we can cause the seq2seq model to generate the designated keyword and even the whole sentence. Extensive experiments on machine translation and text summarization have been conducted to show our proposed methods could achieve over 90% attack success rate on multiple datasets and models.
  arXiv  Detail & Related papers  (2023-05-03T20:31:13Z)
• Turn the Combination Lock: Learnable Textual Backdoor Attacks via Word Substitution [57.51117978504175]
  Recent studies show that neural natural language processing (NLP) models are vulnerable to backdoor attacks. Injected with backdoors, models perform normally on benign examples but produce attacker-specified predictions when the backdoor is activated. We present invisible backdoors that are activated by a learnable combination of word substitution.
  arXiv  Detail & Related papers  (2021-06-11T13:03:17Z)
• BAAAN: Backdoor Attacks Against Autoencoder and GAN-Based Machine Learning Models [21.06679566096713]
  We explore one of the most severe attacks against machine learning models, namely the backdoor attack, against both autoencoders and GANs. The backdoor attack is a training time attack where the adversary implements a hidden backdoor in the target model that can only be activated by a secret trigger. We extend the applicability of backdoor attacks to autoencoders and GAN-based models.
  arXiv  Detail & Related papers  (2020-10-06T20:26:16Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.