paper-with-me

홈 › Papers

Neutralizing Backdoors through Information Conflicts for Large Language Models

2024-11-27 · Chen Chen, Yuchen Sun, Xueluan Gong, Jiaxin Gao, Kwok-Yan Lam

Large language models (LLMs) have seen significant advancements, achieving superior performance in various Natural Language Processing (NLP) tasks, from understanding to reasoning. However, they remain vulnerable to backdoor attacks, where models behave normally for standard queries but generate harmful responses or unintended output when specific triggers are activated. Existing backdoor defenses often suffer from drawbacks that they either focus on detection without removal, rely on rigid assumptions about trigger properties, or prove to be ineffective against advanced attacks like multi-trigger backdoors. In this paper, we present a novel method to eliminate backdoor behaviors from LLMs through the construction of information conflicts using both internal and external mechanisms. Internally, we leverage a lightweight dataset to train a conflict model, which is then merged with the backdoored model to neutralize malicious behaviors by embedding contradictory information within the model's parametric memory. Externally, we incorporate convincing contradictory evidence into the prompt to challenge the model's internal backdoor knowledge. Experimental results on classification and conversational tasks across 4 widely used LLMs demonstrate that our method outperforms 8 state-of-the-art backdoor defense baselines. We can reduce the attack success rate of advanced backdoor attacks by up to 98% while maintaining over 90% clean data accuracy. Furthermore, our method has proven to be robust against adaptive backdoor attacks. The code will be open-sourced upon publication.

📄 PDF Abstract BibTeX arXiv:2411.18280

Code (0)

등록된 구현이 없습니다.

Tasks

backdoor defense

Methods 이 논문이 사용한 방법론

Focus 설명 없음

Similar Papers 제목 키워드 기반

Obliviate: Neutralizing Task-agnostic Backdoors within the Parameter-efficient Fine-tuning Paradigm

2024-09-21 · Jaehan Kim, Minkyoo Song, Seung Ho Na, Seungwon Shin

Parameter-efficient fine-tuning (PEFT) has become a key training strategy for large language models. However, its reliance on fewer trainable parameters poses security risks, such as task-agnostic backdoors. Despite thei…

backdoor defenseparameter-efficient fine-tuning

Act in Collusion: A Persistent Distributed Multi-Target Backdoor in Federated Learning

2024-11-06 · Tao Liu, Wu Yang, Chen Xu, Jiguang Lv 외

Federated learning, a novel paradigm designed to protect data privacy, is vulnerable to backdoor attacks due to its distributed nature. Current research often designs attacks based on a single attacker with a single back…

Backdoor AttackFederated Learning

Removing the Trigger, Not the Backdoor: Alternative Triggers and Latent Backdoors

2026-03-10 · Gorka Abad, Ermes Franch, Stefanos Koffas, Stjepan Picek arxiv

Current backdoor defenses assume that neutralizing a known trigger removes the backdoor. We show this trigger-centric view is incomplete: \emph{alternative triggers}, patterns perceptually distinct from training triggers…

Optimal Smoothing Distribution Exploration for Backdoor Neutralization in Deep Learning-based Traffic Systems

2023-03-24 · Yue Wang, Wending Li, Michail Maniatakos, Saif Eddin Jabari

Deep Reinforcement Learning (DRL) enhances the efficiency of Autonomous Vehicles (AV), but also makes them susceptible to backdoor attacks that can result in traffic congestion or collisions. Backdoor functionality is ty…

Autonomous VehiclesDeep Reinforcement Learningimage-classificationImage Classification

Architectural Backdoors for Within-Batch Data Stealing and Model Inference Manipulation

2025-05-23 · Nicolas Küchler, Ivan Petrov, Conrad Grobler, Ilia Shumailov

For nearly a decade the academic community has investigated backdoors in neural networks, primarily focusing on classification tasks where adversaries manipulate the model prediction. While demonstrably malicious, the im…