Be Kind, Rewrite: Benign Projections via Rewriting Defend Against LLM Data Poisoning Attacks

📅 2026-05-18
📈 Citations: 0
Influential: 0
📄 PDF
🤖 AI Summary
This work addresses the vulnerability of large language models (LLMs) to diverse backdoor attacks and the limited generalizability of existing defenses. The authors propose Open Benign-Based Rewriting (OBBR), a novel mechanism that leverages LLMs themselves to rewrite training data under the guidance of open benign samples, effectively projecting poisoned inputs into a benign prompt space to neutralize harmful content. Theoretical analysis demonstrates that OBBR outperforms conventional closed-book rewriting strategies. Extensive experiments across five distinct backdoor attacks and four mainstream LLMs show that OBBR improves security by 51% over state-of-the-art defenses and by 25.7% compared to closed-book rewriting, while remaining computationally efficient and preserving model performance on clean tasks.
📝 Abstract
Large language models (LLMs) are highly susceptible to backdoor attacks (BAs), wherein training samples are poisoned using trigger-based harmful content. Furthermore, existing defenses have proven ineffective when extensively tested across BA patterns. To better combat BAs, we explore the use of LLM rewriting as a proactive defense against data poisoning. First, we theoretically show that when LLM rewriting utilizes open-book benign samples--termed open-book benign rewriting (OBBR)--the probability of a rewritten output being benign is strictly greater than that of closed-book rewriting. Thus, OBBR neutralizes harmful content by projecting training samples to the space of benign prompts. We then show that, in contrast to previous defenses, OBBR effectively mitigates a large number of existing BAs: across five known BAs and four widely used LLMs, OBBR increases safety performance by an average 51% compared to state-of-the-art BA defenses and 25.7% compared to closed-book rewriting methods. Finally, we show that OBBR is computationally efficient relative to other BA defenses, does not degrade model performance on natural language tasks after fine-tuning, and is capable of defending against non-trigger based data poisoning attacks.
Problem

Research questions and friction points this paper is trying to address.

backdoor attacks
data poisoning
large language models
LLM security
training data integrity
Innovation

Methods, ideas, or system contributions that make the work stand out.

data poisoning defense
backdoor attacks
open-book benign rewriting
large language models
proactive defense
🔎 Similar Papers
No similar papers found.
J
John T. Halloran
Leidos
N
Noopur S. Bhatt
University of Pennsylvania