Cover Image

SLIP: Soft Label Mechanism and Key-Extraction-Guided CoT-based Defense Against Instruction Backdoor in APIs

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wu, Zhengxian, Wen, Juan, Peng, Wanli, Chang, Haowei, Zhou, Yinghan, Xue, Yiming
Format:	Preprint
Published:	2025
Subjects:	Cryptography and Security
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

BeDKD: Backdoor Defense Based on Directional Mapping Module and Adversarial Knowledge Distillation
by: Wu, Zhengxian, et al.
Published: (2025)

BadApex: Backdoor Attack Based on Adaptive Optimization Mechanism of Black-box Large Language Models
by: Wu, Zhengxian, et al.
Published: (2025)

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

Is Your Writing Being Mimicked by AI? Unveiling Imitation with Invisible Watermarks in Creative Writing
by: Zhang, Ziwei, et al.
Published: (2025)

Self-Disguise Attack: Induce the LLM to disguise itself for AIGT detection evasion
by: Zhou, Yinghan, et al.
Published: (2025)

GTSD: Generative Text Steganography Based on Diffusion Model
by: Wu, Zhengxian, et al.
Published: (2025)

TRAP: Hijacking VLA CoT-Reasoning via Adversarial Patches
by: Huang, Zhengxian, et al.
Published: (2026)

EditMF: Drawing an Invisible Fingerprint for Your Large Language Models
by: Wu, Jiaxuan, et al.
Published: (2025)

Nearest is Not Dearest: Towards Practical Defense against Quantization-conditioned Backdoor Attacks
by: Li, Boheng, et al.
Published: (2024)

CoSPED: Consistent Soft Prompt Targeted Data Extraction and Defense
by: Yang, Zhuochen, et al.
Published: (2025)

Critical-CoT: A Robust Defense Framework against Reasoning-Level Backdoor Attacks in Large Language Models
by: Truong, Vu Tuan, et al.
Published: (2026)

Instruction Backdoor Attacks Against Customized LLMs
by: Zhang, Rui, et al.
Published: (2024)

E-SAGE: Explainability-based Defense Against Backdoor Attacks on Graph Neural Networks
by: Yuan, Dingqiang, et al.
Published: (2024)

Soft Instruction De-escalation Defense
by: Walter, Nils Philipp, et al.
Published: (2025)

PECAN: A Deterministic Certified Defense Against Backdoor Attacks
by: Zhang, Yuhao, et al.
Published: (2023)

Diffusion-Guided Adversarial Perturbation Injection for Generalizable Defense Against Facial Manipulations
by: Li, Yue, et al.
Published: (2026)

ADAGE: Active Defenses Against GNN Extraction
by: Xu, Jing, et al.
Published: (2025)

KDk: A Defense Mechanism Against Label Inference Attacks in Vertical Federated Learning
by: Arazzi, Marco, et al.
Published: (2024)

CoTDeceptor:Adversarial Code Obfuscation Against CoT-Enhanced LLM Code Agents
by: Li, Haoyang, et al.
Published: (2025)

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

TED-LaST: Towards Robust Backdoor Defense Against Adaptive Attacks
by: Mo, Xiaoxing, et al.
Published: (2025)

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)

Adversarially Guided Stateful Defense Against Backdoor Attacks in Federated Deep Learning
by: Ali, Hassan, et al.
Published: (2024)

SLIP-SEC: Formalizing Secure Protocols for Model IP Protection
by: Jain, Racchit, et al.
Published: (2025)

GANcrop: A Contrastive Defense Against Backdoor Attacks in Federated Learning
by: Gan, Xiaoyun, et al.
Published: (2024)

AntiFLipper: A Secure and Efficient Defense Against Label-Flipping Attacks in Federated Learning
by: Rahman, Aashnan, et al.
Published: (2025)

Jailbreaking LLMs & VLMs: Mechanisms, Evaluation, and Unified Defense
by: Chen, Zejian, et al.
Published: (2026)

HoneypotNet: Backdoor Attacks Against Model Extraction
by: Wang, Yixu, et al.
Published: (2025)

TrojanEdit: Multimodal Backdoor Attack Against Image Editing Model
by: Guo, Ji, et al.
Published: (2024)

Backdoor-Powered Prompt Injection Attacks Nullify Defense Methods
by: Chen, Yulin, et al.
Published: (2025)

Backdoor Attacks and Defenses in Computer Vision Domain: A Survey
by: Abbasi, Bilal Hussain, et al.
Published: (2025)

Distributed Backdoor Attacks on Federated Graph Learning and Certified Defenses
by: Yang, Yuxin, et al.
Published: (2024)

TrapSuffix: Proactive Defense Against Adversarial Suffixes in Jailbreaking
by: Du, Mengyao, et al.
Published: (2026)

SoK: The Last Line of Defense: On Backdoor Defense Evaluation
by: Abad, Gorka, et al.
Published: (2025)

Seal Your Backdoor with Variational Defense
by: Sabolić, Ivan, et al.
Published: (2025)

Robustness Inspired Graph Backdoor Defense
by: Zhang, Zhiwei, et al.
Published: (2024)

Retrieval-Confused Generation is a Good Defender for Privacy Violation Attack of Large Language Models
by: Peng, Wanli, et al.
Published: (2025)

MisGUIDE : Defense Against Data-Free Deep Learning Model Extraction
by: Gurve, Mahendra, et al.
Published: (2024)

Architectural Backdoors in Deep Learning: A Survey of Vulnerabilities, Detection, and Defense
by: Childress, Victoria, et al.
Published: (2025)

Attack as Defense: Run-time Backdoor Implantation for Image Content Protection
by: Zhang, Haichuan, et al.
Published: (2024)