Copertina

PEPPER: Perception-Guided Perturbation for Robust Backdoor Defense in Text-to-Image Diffusion Models

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Chew, Oscar, Lu, Po-Yi, Lin, Jayden, Huang, Kuan-Hao, Lin, Hsuan-Tien
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Defending Text-to-image Diffusion Models: Surprising Efficacy of Textual Perturbations Against Backdoor Attacks
di: Chew, Oscar, et al.
Pubblicazione: (2024)

Understanding and Mitigating Spurious Correlations in Text Classification with Neighborhood Analysis
di: Chew, Oscar, et al.
Pubblicazione: (2023)

Comparison between the Structures of Word Co-occurrence and Word Similarity Networks for Ill-formed and Well-formed Texts in Taiwan Mandarin
di: Huang, Po-Hsuan, et al.
Pubblicazione: (2024)

Pop-Up Distractions Reveal Bag-of-Events Behavior in Video Large Language Models
di: Chew, Oscar, et al.
Pubblicazione: (2026)

Exploring Backdoor Vulnerabilities of Chat Models
di: Hao, Yunzhuo, et al.
Pubblicazione: (2024)

BadGraph: A Backdoor Attack Against Latent Diffusion Model for Text-Guided Graph Generation
di: Ye, Liang, et al.
Pubblicazione: (2025)

Expanding the Role of Diffusion Models for Robust Classifier Training
di: Huang, Pin-Han, et al.
Pubblicazione: (2026)

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

Pruning Strategies for Backdoor Defense in LLMs
di: Chapagain, Santosh, et al.
Pubblicazione: (2025)

Scaling Concept With Text-Guided Diffusion Models
di: Huang, Chao, et al.
Pubblicazione: (2024)

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

Are AI-Generated Text Detectors Robust to Adversarial Perturbations?
di: Huang, Guanhua, et al.
Pubblicazione: (2024)

Two Heads are Better than One: Nested PoE for Robust Defense Against Multi-Backdoors
di: Graf, Victoria, et al.
Pubblicazione: (2024)

The Role of Exploration Modules in Small Language Models for Knowledge Graph Question Answering
di: Cheng, Yi-Jie, et al.
Pubblicazione: (2025)

Improving Sampling for Masked Diffusion Models via Information Gain
di: Yang, Kaisen, et al.
Pubblicazione: (2026)

Defensive Dual Masking for Robust Adversarial Defense
di: Yang, Wangli, et al.
Pubblicazione: (2024)

Improving LLM Unlearning Robustness via Random Perturbations
di: Huu-Tien, Dang, et al.
Pubblicazione: (2025)

Effective Unsupervised Constrained Text Generation based on Perturbed Masking
di: Fu, Yingwen, et al.
Pubblicazione: (2024)

Is CLIP Cross-Eyed? Revealing and Mitigating Center Bias in the CLIP Family
di: Chew, Oscar, et al.
Pubblicazione: (2026)

TASTE: Text-Aligned Speech Tokenization and Embedding for Spoken Language Modeling
di: Tseng, Liang-Hsuan, et al.
Pubblicazione: (2025)

Defense Against Syntactic Textual Backdoor Attacks with Token Substitution
di: Li, Xinglin, et al.
Pubblicazione: (2024)

Test-time Backdoor Mitigation for Black-Box Large Language Models with Defensive Demonstrations
di: Mo, Wenjie, et al.
Pubblicazione: (2023)

UniGuardian: A Unified Defense for Detecting Prompt Injection, Backdoor Attacks and Adversarial Attacks in Large Language Models
di: Lin, Huawei, et al.
Pubblicazione: (2025)

ASCIIEval: Benchmarking Models' Visual Perception in Text Strings via ASCII Art
di: Jia, Qi, et al.
Pubblicazione: (2024)

DEEM: Diffusion Models Serve as the Eyes of Large Language Models for Image Perception
di: Luo, Run, et al.
Pubblicazione: (2024)

Backdoor Collapse: Eliminating Unknown Threats via Known Backdoor Aggregation in Language Models
di: Lin, Liang, et al.
Pubblicazione: (2025)

SynCPKL: Harnessing LLMs to Generate Synthetic Data for Commonsense Persona Knowledge Linking
di: Lin, Kuan-Yen
Pubblicazione: (2024)

Navigating the Risks of Using Large Language Models for Text Annotation in Social Science Research
di: Lin, Hao, et al.
Pubblicazione: (2025)

Merging Triggers, Breaking Backdoors: Defensive Poisoning for Instruction-Tuned Language Models
di: Kim, San, et al.
Pubblicazione: (2026)

One Model, Many Morals: Uncovering Cross-Linguistic Misalignments in Computational Moral Reasoning
di: Farid, Sualeha, et al.
Pubblicazione: (2025)

Investigating Zero-Shot Generalizability on Mandarin-English Code-Switched ASR and Speech-to-text Translation of Recent Foundation Models with Self-Supervision and Weak Supervision
di: Yang, Chih-Kai, et al.
Pubblicazione: (2023)

Image2Text2Image: A Novel Framework for Label-Free Evaluation of Image-to-Text Generation with Text-to-Image Diffusion Models
di: Huang, Jia-Hong, et al.
Pubblicazione: (2024)

Semantically-Aware LLM Agent to Enhance Privacy in Conversational AI Services
di: Serenari, Jayden, et al.
Pubblicazione: (2025)

A Survey of Recent Backdoor Attacks and Defenses in Large Language Models
di: Zhao, Shuai, et al.
Pubblicazione: (2024)

A Reparameterized Discrete Diffusion Model for Text Generation
di: Zheng, Lin, et al.
Pubblicazione: (2023)

Profiling Patient Transcript Using Large Language Model Reasoning Augmentation for Alzheimer's Disease Detection
di: Chen, Chin-Po, et al.
Pubblicazione: (2024)

Robust Biomedical Publication Type and Study Design Classification with Knowledge-Guided Perturbations
di: Ming, Shufan, et al.
Pubblicazione: (2026)

Unifying Adversarial Robustness and Training Across Text Scoring Models
di: Tamber, Manveer Singh, et al.
Pubblicazione: (2026)

Prompting4Debugging: Red-Teaming Text-to-Image Diffusion Models by Finding Problematic Prompts
di: Chin, Zhi-Yi, et al.
Pubblicazione: (2023)

AEIOU: A Unified Defense Framework against NSFW Prompts in Text-to-Image Models
di: Wang, Yiming, et al.
Pubblicazione: (2024)