Copertina

BURN: Backdoor Unlearning via Adversarial Boundary Analysis

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Su, Yanghao, Zhang, Jie, Li, Yiming, Zhang, Tianwei, Guo, Qing, Zhang, Weiming, Yu, Nenghai, Lukas, Nils, Zhou, Wenbo
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Cryptography and Security
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Model X-ray:Detecting Backdoored Models via Decision Boundary
di: Su, Yanghao, et al.
Pubblicazione: (2024)

Character as a Latent Variable in Large Language Models: A Mechanistic Account of Emergent Misalignment and Conditional Safety Failures
di: Su, Yanghao, et al.
Pubblicazione: (2026)

AquaLoRA: Toward White-box Protection for Customized Stable Diffusion Models via Watermark LoRA
di: Feng, Weitao, et al.
Pubblicazione: (2024)

State-Dependent Safety Failures in Multi-Turn Language Model Interaction
di: Li, Pengcheng, et al.
Pubblicazione: (2026)

SafeGuider: Robust and Practical Content Safety Control for Text-to-Image Models
di: Qi, Peigui, et al.
Pubblicazione: (2025)

InferDPT: Privacy-Preserving Inference for Closed-box Large Language Model
di: Tong, Meng, et al.
Pubblicazione: (2023)

Exploiting Vulnerabilities in Speech Translation Systems through Targeted Adversarial Attacks
di: Liu, Chang, et al.
Pubblicazione: (2025)

Turning Your Strength into Watermark: Watermarking Large Language Model via Knowledge Injection
di: Li, Shuai, et al.
Pubblicazione: (2023)

SQL Injection Jailbreak: A Structural Disaster of Large Language Models
di: Zhao, Jiawei, et al.
Pubblicazione: (2024)

Performance-lossless Black-box Model Watermarking
di: Zhao, Na, et al.
Pubblicazione: (2023)

PSRT: Accelerating LRM-based Guard Models via Prefilled Safe Reasoning Traces
di: Zhao, Jiawei, et al.
Pubblicazione: (2025)

CamLoPA: A Hidden Wireless Camera Localization Framework via Signal Propagation Path Analysis
di: Zhang, Xiang, et al.
Pubblicazione: (2024)

On the Vulnerability of Text Sanitization
di: Tong, Meng, et al.
Pubblicazione: (2024)

Natias: Neuron Attribution based Transferable Image Adversarial Steganography
di: Fan, Zexin, et al.
Pubblicazione: (2024)

FoC: Figure out the Cryptographic Functions in Stripped Binaries with LLMs
di: Shang, Xiuwei, et al.
Pubblicazione: (2024)

A high-capacity linguistic steganography based on entropy-driven rank-token mapping
di: Jiang, Jun, et al.
Pubblicazione: (2025)

EditMark: Watermarking Large Language Models based on Model Editing
di: Li, Shuai, et al.
Pubblicazione: (2025)

Invisibility Cloak: Disappearance under Human Pose Estimation via Backdoor Attacks
di: Zhang, Minxing, et al.
Pubblicazione: (2024)

PoseGuard: Pose-Guided Generation with Safety Guardrails
di: Wang, Kongxin, et al.
Pubblicazione: (2025)

SSD: A State-based Stealthy Backdoor Attack For Navigation System in UAV Route Planning
di: Wang, Zhaoxuan, et al.
Pubblicazione: (2025)

Provably Secure Public-Key Steganography Based on Admissible Encoding
di: Zhang, Xin, et al.
Pubblicazione: (2025)

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

GIFDL: Generated Image Fluctuation Distortion Learning for Enhancing Steganographic Security
di: Wang, Xiangkun, et al.
Pubblicazione: (2025)

Silent Guardian: Protecting Text from Malicious Exploitation by Large Language Models
di: Zhao, Jiawei, et al.
Pubblicazione: (2023)

Backdoor Attacks against Hybrid Classical-Quantum Neural Networks
di: Guo, Ji, et al.
Pubblicazione: (2024)

Beyond the Edge of Function: Unraveling the Patterns of Type Recovery in Binary Code
di: Li, Gangyang, et al.
Pubblicazione: (2025)

Coward: Collision-based OOD Watermarking for Practical Proactive Federated Backdoor Detection
di: Li, Wenjie, et al.
Pubblicazione: (2025)

Stealthy Targeted Backdoor Attacks against Image Captioning
di: Fan, Wenshu, et al.
Pubblicazione: (2024)

Provably Secure Agent Guardrail
di: Wu, Benlong, et al.
Pubblicazione: (2026)

Provably Secure Disambiguating Neural Linguistic Steganography
di: Qi, Yuang, et al.
Pubblicazione: (2024)

The Gradient Puppeteer: Adversarial Domination in Gradient Leakage Attacks through Model Poisoning
di: Xiang, Kunlan, et al.
Pubblicazione: (2025)

"No Matter What You Do": Purifying GNN Models via Backdoor Unlearning
di: Zhang, Jiale, et al.
Pubblicazione: (2024)

BadTemplate: A Training-Free Backdoor Attack via Chat Template Against Large Language Models
di: Wang, Zihan, et al.
Pubblicazione: (2026)

Really Unlearned? Verifying Machine Unlearning via Influential Sample Pairs
di: Xu, Heng, et al.
Pubblicazione: (2024)

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

BadFU: Backdoor Federated Learning through Adversarial Machine Unlearning
di: Lu, Bingguang, et al.
Pubblicazione: (2025)

Transferable Backdoor Attacks for Code Models via Sharpness-Aware Adversarial Perturbation
di: Chang, Shuyu, et al.
Pubblicazione: (2026)

Backdoor Attacks against Image-to-Image Networks
di: Jiang, Wenbo, et al.
Pubblicazione: (2024)

STEAD: Robust Provably Secure Linguistic Steganography with Diffusion Language Model
di: Qi, Yuang, et al.
Pubblicazione: (2026)

Unlearn and Burn: Adversarial Machine Unlearning Requests Destroy Model Accuracy
di: Huang, Yangsibo, et al.
Pubblicazione: (2024)