paper-with-me

Papers

Mitigating Backdoor Threats to Large Language Models: Advancement and Challenges

2024-09-30 · Qin Liu, Wenjie Mo, Terry Tong, Jiashu Xu, Fei Wang, Chaowei Xiao, Muhao Chen

The advancement of Large Language Models (LLMs) has significantly impacted various domains, including Web search, healthcare, and software development. However, as these models scale, they become more vulnerable to cybersecurity risks, particularly backdoor attacks. By exploiting the potent memorization capacity of LLMs, adversaries can easily inject backdoors into LLMs by manipulating a small portion of training data, leading to malicious behaviors in downstream applications whenever the hidden backdoor is activated by the pre-defined triggers. Moreover, emerging learning paradigms like instruction tuning and reinforcement learning from human feedback (RLHF) exacerbate these risks as they rely heavily on crowdsourced data and human feedback, which are not fully controlled. In this paper, we present a comprehensive survey of emerging backdoor threats to LLMs that appear during LLM development or inference, and cover recent advancement in both defense and detection strategies for mitigating backdoor threats to LLMs. We also outline key challenges in addressing these threats, highlighting areas for future research.

📄 PDF Abstract BibTeX arXiv:2409.19993

Code (0)

등록된 구현이 없습니다.

Tasks

Memorization

Similar Papers 제목 키워드 기반

BackdoorVLM: A Benchmark for Backdoor Attacks on Vision-Language Models

2025-11-24 · Juncheng Li, Yige Li, Hanxun Huang, Yunhao Chen 외 arxiv

Backdoor attacks undermine the reliability and trustworthiness of machine learning systems by injecting hidden behaviors that can be maliciously activated at inference time. While such threats have been extensively studi…

Visual Question AnsweringImage Captioning

Angel or Demon: Investigating the Plasticity Interventions' Impact on Backdoor Threats in Deep Reinforcement Learning

2026-05-14 · Oubo Ma, Ruixiao Lin, Yang Dai, Jiahao Chen 외 arxiv

Extensive research has highlighted the severe threats posed by backdoor attacks to deep reinforcement learning (DRL). However, prior studies primarily focus on vanilla scenarios, while plasticity interventions have emerg…

Reinforcement Learning

Imperio: Language-Guided Backdoor Attacks for Arbitrary Model Control

2024-01-02 · Ka-Ho Chow, Wenqi Wei, Lei Yu

Natural language processing (NLP) has received unprecedented attention. While advancements in NLP models have led to extensive research into their backdoor vulnerabilities, the potential for these advancements to introdu…

Backdoor AttackImage ClassificationLanguage ModelingLanguage Modelling

A Survey on Backdoor Threats in Large Language Models (LLMs): Attacks, Defenses, and Evaluations

2025-02-06 · Yihe Zhou, Tao Ni, Wei-Bin Lee, Qingchuan Zhao

Large Language Models (LLMs) have achieved significantly advanced capabilities in understanding and generating human language text, which have gained increasing popularity over recent years. Apart from their state-of-the…

Efficient Backdoor Defense in Multimodal Contrastive Learning: A Token-Level Unlearning Method for Mitigating Threats

2024-09-29 · Kuanrong Liu, Siyuan Liang, Jiawei Liang, Pengwen Dai 외

Multimodal contrastive learning uses various data modalities to create high-quality features, but its reliance on extensive data sources on the Internet makes it vulnerable to backdoor attacks. These attacks insert malic…

Backdoor Attackbackdoor defenseContrastive LearningMachine Unlearning