Cover Image

Cut the Deadwood Out: Backdoor Purification via Guided Module Substitution

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Tong, Yao, Li, Weijun, He, Xuanli, Zhan, Haolan, Xu, Qiongkai
Format:	Preprint
Published:	2024
Subjects:	Computation and Language Cryptography and Security
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Defending against Backdoor Attacks via Module Switching
by: Li, Weijun, et al.
Published: (2025)

SEEP: Training Dynamics Grounds Latent Representation Search for Mitigating Backdoor Poisoning Attacks
by: He, Xuanli, et al.
Published: (2024)

TuBA: Cross-Lingual Transferability of Backdoor Attacks in LLMs with Instruction Tuning
by: He, Xuanli, et al.
Published: (2024)

WARDEN: Multi-Directional Backdoor Watermarks for Embedding-as-a-Service Copyright Protection
by: Shetty, Anudeex, et al.
Published: (2024)

Beyond Theoretical Bounds: Empirical Privacy Loss Calibration for Text Rewriting Under Local Differential Privacy
by: Li, Weijun, et al.
Published: (2026)

Attacks on Third-Party APIs of Large Language Models
by: Zhao, Wanru, et al.
Published: (2024)

Seeing the Forest through the Trees: Data Leakage from Partial Transformer Gradients
by: Li, Weijun, et al.
Published: (2024)

DUP: Detection-guided Unlearning for Backdoor Purification in Language Models
by: Hu, Man, et al.
Published: (2025)

Compiling Activation Steering into Weights via Null-Space Constraints for Stealthy Backdoors
by: Yin, Rui, et al.
Published: (2026)

WET: Overcoming Paraphrasing Vulnerabilities in Embeddings-as-a-Service with Linear Transformation Watermarks
by: Shetty, Anudeex, et al.
Published: (2024)

Generative Models are Self-Watermarked: Declaring Model Authentication through Re-Generation
by: Desu, Aditya, et al.
Published: (2024)

BadActs: A Universal Backdoor Defense in the Activation Space
by: Yi, Biao, et al.
Published: (2024)

Trojan-Speak: Bypassing Constitutional Classifiers with No Jailbreak Tax via Adversarial Finetuning
by: Sel, Bilgehan, et al.
Published: (2026)

Segment-Level Coherence for Robust Harmful Intent Probing in LLMs
by: He, Xuanli, et al.
Published: (2026)

Watch Out for Your Guidance on Generation! Exploring Conditional Backdoor Attacks against Large Language Models
by: He, Jiaming, et al.
Published: (2024)

Watch Out for Your Agents! Investigating Backdoor Threats to LLM-Based Agents
by: Yang, Wenkai, et al.
Published: (2024)

Probe before You Talk: Towards Black-box Defense against Backdoor Unalignment for Large Language Models
by: Yi, Biao, et al.
Published: (2025)

Data Extraction Attacks in Retrieval-Augmented Generation via Backdoors
by: Peng, Yuefeng, et al.
Published: (2024)

MetaBackdoor: Exploiting Positional Encoding as a Backdoor Attack Surface in LLMs
by: Wen, Rui, et al.
Published: (2026)

ConfGuard: A Simple and Effective Backdoor Detection for Large Language Models
by: Wang, Zihan, et al.
Published: (2025)

Claim-Guided Textual Backdoor Attack for Practical Applications
by: Song, Minkyoo, et al.
Published: (2024)

IDT: Dual-Task Adversarial Attacks for Privacy Protection
by: Faustini, Pedro, et al.
Published: (2024)

BadLingual: A Novel Lingual-Backdoor Attack against Large Language Models
by: Wang, Zihan, et al.
Published: (2025)

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

BAIT: Boundary-Guided Disclosure Escalation via Self-Conditioned Reasoning
by: Luo, Xuan, et al.
Published: (2026)

Simulate and Eliminate: Revoke Backdoors for Generative Large Language Models
by: Li, Haoran, et al.
Published: (2024)

Large Language Models are Good Attackers: Efficient and Stealthy Textual Backdoor Attacks
by: Li, Ziqiang, et al.
Published: (2024)

PRISM: Privacy-Aware Routing for Adaptive Cloud-Edge LLM Inference via Semantic Sketch Collaboration
by: Zhan, Junfei, et al.
Published: (2025)

BadJudge: Backdoor Vulnerabilities of LLM-as-a-Judge
by: Tong, Terry, et al.
Published: (2025)

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

ALGEN: Few-shot Inversion Attacks on Textual Embeddings using Alignment and Generation
by: Chen, Yiyi, et al.
Published: (2025)

Task-Agnostic Detector for Insertion-Based Backdoor Attacks
by: Lyu, Weimin, et al.
Published: (2024)

Backdoor Token Unlearning: Exposing and Defending Backdoors in Pretrained Language Models
by: Jiang, Peihai, et al.
Published: (2025)

Hidden Ads: Behavior Triggered Semantic Backdoors for Advertisement Injection in Vision Language Models
by: Yao, Duanyi, et al.
Published: (2026)

ShadowCoT: Cognitive Hijacking for Stealthy Reasoning Backdoors in LLMs
by: Zhao, Gejian, et al.
Published: (2025)

Eguard: Defending LLM Embeddings Against Inversion Attacks via Text Mutual Information Optimization
by: Liu, Tiantian, et al.
Published: (2024)

Where Do Backdoors Live? A Component-Level Analysis of Backdoor Propagation in Speech Language Models
by: Fortier, Alexandrine, et al.
Published: (2025)

LexiMark: Robust Watermarking via Lexical Substitutions to Enhance Membership Verification of an LLM's Textual Training Data
by: German, Eyal, et al.
Published: (2025)

MBTSAD: Mitigating Backdoors in Language Models Based on Token Splitting and Attention Distillation
by: Ding, Yidong, et al.
Published: (2025)

bi-GRPO: Bidirectional Optimization for Jailbreak Backdoor Injection on LLMs
by: Ji, Wence, et al.
Published: (2025)