Copertina

Espresso: Robust Concept Filtering in Text-to-Image Models

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Das, Anudeep, Duddu, Vasisht, Zhang, Rui, Asokan, N.
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Computer Vision and Pattern Recognition Cryptography and Security
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Do Concept Replacement Techniques Really Erase Unacceptable Concepts?
di: Das, Anudeep, et al.
Pubblicazione: (2025)

Locket: Robust Feature-Locking Technique for Language Models
di: He, Lipeng, et al.
Pubblicazione: (2025)

Combining Machine Learning Defenses without Conflicts
di: Duddu, Vasisht, et al.
Pubblicazione: (2024)

Attesting Distributional Properties of Training Data for Machine Learning
di: Duddu, Vasisht, et al.
Pubblicazione: (2023)

TwoHamsters: Benchmarking Multi-Concept Compositional Unsafety in Text-to-Image Models
di: Zhang, Chaoshuo, et al.
Pubblicazione: (2026)

SoK: Unintended Interactions among Machine Learning Defenses and Risks
di: Duddu, Vasisht, et al.
Pubblicazione: (2023)

Neighbor-Aware Localized Concept Erasure in Text-to-Image Diffusion Models
di: Shi, Zhuan, et al.
Pubblicazione: (2026)

SurrogatePrompt: Bypassing the Safety Filter of Text-to-Image Models via Substitution
di: Ba, Zhongjie, et al.
Pubblicazione: (2023)

Beyond Text Prompts: Precise Concept Erasure through Text-Image Collaboration
di: Li, Jun, et al.
Pubblicazione: (2026)

PATCH: Mitigating PII Leakage in Language Models with Privacy-Aware Targeted Circuit PatcHing
di: Hughes, Anthony, et al.
Pubblicazione: (2025)

Rethinking Robust Adversarial Concept Erasure in Diffusion Models
di: Yin, Qinghong, et al.
Pubblicazione: (2025)

Defensive Unlearning with Adversarial Training for Robust Concept Erasure in Diffusion Models
di: Zhang, Yimeng, et al.
Pubblicazione: (2024)

One Prompt to Verify Your Models: Black-Box Text-to-Image Models Verification via Non-Transferable Adversarial Attacks
di: Guo, Ji, et al.
Pubblicazione: (2024)

Six-CD: Benchmarking Concept Removals for Benign Text-to-image Diffusion Models
di: Ren, Jie, et al.
Pubblicazione: (2024)

Laminator: Verifiable ML Property Cards using Hardware-assisted Attestations
di: Duddu, Vasisht, et al.
Pubblicazione: (2024)

FedSECA: Sign Election and Coordinate-wise Aggregation of Gradients for Byzantine Tolerant Federated Learning
di: Benjamin, Joseph Geo, et al.
Pubblicazione: (2024)

Sparse Autoencoder as a Zero-Shot Classifier for Concept Erasing in Text-to-Image Diffusion Models
di: Tian, Zhihua, et al.
Pubblicazione: (2025)

Patronus: Safeguarding Text-to-Image Models against White-Box Adversaries
di: Li, Xinfeng, et al.
Pubblicazione: (2025)

Guarding the Gate: ConceptGuard Battles Concept-Level Backdoors in Concept Bottleneck Models
di: Lai, Songning, et al.
Pubblicazione: (2024)

CAT: Concept-level backdoor ATtacks for Concept Bottleneck Models
di: Lai, Songning, et al.
Pubblicazione: (2024)

Detecting Malicious Concepts without Image Generation in AI-Generated Content (AIGC)
di: Xu, Kun, et al.
Pubblicazione: (2025)

VideoEraser: Concept Erasure in Text-to-Video Diffusion Models
di: Xu, Naen, et al.
Pubblicazione: (2025)

HTS-Attack: Heuristic Token Search for Jailbreaking Text-to-Image Models
di: Gao, Sensen, et al.
Pubblicazione: (2024)

Token-Level Constraint Boundary Search for Jailbreaking Text-to-Image Models
di: Liu, Jiangtao, et al.
Pubblicazione: (2025)

Membership Inference on Text-to-Image Diffusion Models via Conditional Likelihood Discrepancy
di: Zhai, Shengfang, et al.
Pubblicazione: (2024)

REDEditing: Relationship-Driven Precise Backdoor Poisoning on Text-to-Image Diffusion Models
di: Guo, Chongye, et al.
Pubblicazione: (2025)

IConMark: Robust Interpretable Concept-Based Watermark For AI Images
di: Sadasivan, Vinu Sankar, et al.
Pubblicazione: (2025)

Intriguing Properties of Diffusion Models: An Empirical Study of the Natural Attack Capability in Text-to-Image Generative Models
di: Sato, Takami, et al.
Pubblicazione: (2023)

FT-Shield: A Watermark Against Unauthorized Fine-tuning in Text-to-Image Diffusion Models
di: Cui, Yingqian, et al.
Pubblicazione: (2023)

BadBlocks: Low-Cost and Stealthy Backdoor Attacks Tailored for Text-to-Image Diffusion Models
di: Wu, Jia, et al.
Pubblicazione: (2025)

SafeText: Safe Text-to-image Models via Aligning the Text Encoder
di: Hu, Yuepeng, et al.
Pubblicazione: (2025)

PAL*M: Property Attestation for Large Generative Models
di: Chantasantitam, Prach, et al.
Pubblicazione: (2026)

Secure and Robust Watermarking for AI-generated Images: A Comprehensive Survey
di: Cao, Jie, et al.
Pubblicazione: (2025)

Hidden Tail: Adversarial Image Causing Stealthy Resource Consumption in Vision-Language Models
di: Zhang, Rui, et al.
Pubblicazione: (2025)

CoreMark: Toward Robust and Universal Text Watermarking Technique
di: Meng, Jiale, et al.
Pubblicazione: (2025)

Bi-Erasing: A Bidirectional Framework for Concept Removal in Diffusion Models
di: Chen, Hao, et al.
Pubblicazione: (2025)

What Concepts Lie Within? Detecting and Suppressing Risky Content in Diffusion Transformers
di: Zhang, Chenyu
Pubblicazione: (2026)

Scaling Exposes the Trigger: Input-Level Backdoor Detection in Text-to-Image Diffusion Models via Cross-Attention Scaling
di: Li, Zida, et al.
Pubblicazione: (2026)

Two Frames Matter: A Temporal Attack for Text-to-Video Model Jailbreaking
di: Chen, Moyang, et al.
Pubblicazione: (2026)

When Memory Becomes a Vulnerability: Towards Multi-turn Jailbreak Attacks against Text-to-Image Generation Systems
di: Zhao, Shiqian, et al.
Pubblicazione: (2025)