Cover Image

BEEAR: Embedding-based Adversarial Removal of Safety Backdoors in Instruction-tuned Language Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zeng, Yi, Sun, Weiyu, Huynh, Tran Ngoc, Song, Dawn, Li, Bo, Jia, Ruoxi
Format:	Preprint
Published:	2024
Subjects:	Cryptography and Security Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Double Backdoored: Converting Code Large Language Model Backdoors to Traditional Malware via Adversarial Instruction Tuning Attacks
by: Hossen, Md Imran, et al.
Published: (2024)

RigorLLM: Resilient Guardrails for Large Language Models against Undesired Content
by: Yuan, Zhuowen, et al.
Published: (2024)

Mitigating Fine-tuning based Jailbreak Attack with Backdoor Enhanced Safety Alignment
by: Wang, Jiongxiao, et al.
Published: (2024)

A Study of Backdoors in Instruction Fine-tuned Language Models
by: Raghuram, Jayaram, et al.
Published: (2024)

DiffAttack: Evasion Attacks Against Diffusion-Based Adversarial Purification
by: Kang, Mintong, et al.
Published: (2023)

BaThe: Defense against the Jailbreak Attack in Multimodal Large Language Models by Treating Harmful Instruction as Backdoor Trigger
by: Chen, Yulin, et al.
Published: (2024)

Backdoor Contrastive Learning via Bi-level Trigger Optimization
by: Sun, Weiyu, et al.
Published: (2024)

Iterative Window Mean Filter: Thwarting Diffusion-based Adversarial Purification
by: Wang, Hanrui, et al.
Published: (2024)

Inhibitory Attacks on Backdoor-based Fingerprinting for Large Language Models
by: Fu, Hang, et al.
Published: (2026)

Instructions as Backdoors: Backdoor Vulnerabilities of Instruction Tuning for Large Language Models
by: Xu, Jiashu, et al.
Published: (2023)

SoK: The Security-Safety Continuum of Multimodal Foundation Models through Information Flow and Global Game-Theoretic Analysis of Asymmetric Threats
by: Sun, Ruoxi, et al.
Published: (2024)

BadDLM: Backdooring Diffusion Language Models with Diverse Targets
by: Zhai, Shengfang, et al.
Published: (2026)

Adversary-Aware DPO: Enhancing Safety Alignment in Vision Language Models via Adversarial Training
by: Weng, Fenghua, et al.
Published: (2025)

Merge Hijacking: Backdoor Attacks to Model Merging of Large Language Models
by: Yuan, Zenghui, et al.
Published: (2025)

BURN: Backdoor Unlearning via Adversarial Boundary Analysis
by: Su, Yanghao, et al.
Published: (2025)

Efficient Input-level Backdoor Defense on Text-to-Image Synthesis via Neuron Activation Variation
by: Zhai, Shengfang, et al.
Published: (2025)

Perturb and Recover: Fine-tuning for Effective Backdoor Removal from CLIP
by: Singh, Naman Deep, et al.
Published: (2024)

Rethinking Backdoor Detection Evaluation for Language Models
by: Yan, Jun, et al.
Published: (2024)

Data Free Backdoor Attacks
by: Cao, Bochuan, et al.
Published: (2024)

PBP: Post-training Backdoor Purification for Malware Classifiers
by: Nguyen, Dung Thuy, et al.
Published: (2024)

InverTune: Removing Backdoors from Multimodal Contrastive Learning Models via Trigger Inversion and Activation Tuning
by: Sun, Mengyuan, et al.
Published: (2025)

Decompiling Smart Contracts with a Large Language Model
by: David, Isaac, et al.
Published: (2025)

Antidote: Post-fine-tuning Safety Alignment for Large Language Models against Harmful Fine-tuning
by: Huang, Tiansheng, et al.
Published: (2024)

BadToken: Token-level Backdoor Attacks to Multi-modal Large Language Models
by: Yuan, Zenghui, et al.
Published: (2025)

Cross-Modal Backdoors in Multimodal Large Language Models
by: Wang, Runhe, et al.
Published: (2026)

Removing the Trigger, Not the Backdoor: Alternative Triggers and Latent Backdoors
by: Abad, Gorka, et al.
Published: (2026)

Backdoor Attribution: Elucidating and Controlling Backdoor in Language Models
by: Yu, Miao, et al.
Published: (2025)

Ablating Safety: Mechanisms for Removing Alignment in Language Models for Security Applications
by: David, Isaac, et al.
Published: (2026)

SLIP: Soft Label Mechanism and Key-Extraction-Guided CoT-based Defense Against Instruction Backdoor in APIs
by: Wu, Zhengxian, et al.
Published: (2025)

On the Adversarial Robustness of Instruction-Tuned Large Language Models for Code
by: Hossen, Md Imran, et al.
Published: (2024)

Unified Neural Backdoor Removal with Only Few Clean Samples through Unlearning and Relearning
by: Min, Nay Myat, et al.
Published: (2024)

Fine-tuning is Not Fine: Mitigating Backdoor Attacks in GNNs with Limited Clean Data
by: Zhang, Jiale, et al.
Published: (2025)

Robust Anti-Backdoor Instruction Tuning in LVLMs
by: Xun, Yuan, et al.
Published: (2025)

Transferring Backdoors between Large Language Models by Knowledge Distillation
by: Cheng, Pengzhou, et al.
Published: (2024)

ProtegoFed: Backdoor-Free Federated Instruction Tuning with Interspersed Poisoned Data
by: Zhao, Haodong, et al.
Published: (2026)

Backdooring Instruction-Tuned Large Language Models with Virtual Prompt Injection
by: Yan, Jun, et al.
Published: (2023)

Adversarially Robust Assembly Language Model for Packed Executables Detection
by: Li, Shijia, et al.
Published: (2025)

TrojFM: Resource-efficient Backdoor Attacks against Very Large Foundation Models
by: Nie, Yuzhou., et al.
Published: (2024)

Backdoor Cleaning without External Guidance in MLLM Fine-tuning
by: Rong, Xuankun, et al.
Published: (2025)

Stateful Agent Backdoor
by: Dai, Zhengchunmin, et al.
Published: (2026)