No article text was recorded for this version.
passive defense limitations
Version 1 of 149 papers56 conceptsfrozen 2026-10-04
Papers in this version
- Blog: A Systematic Review on Model Watermarking for Neural Networks
- Blog: Intellectual Property Protection for Deep Learning Models: Taxonomy, Methods, Attacks, and Evaluations
- Blog: MLCapsule: Guarded Offline Deployment of Machine Learning as a Service
- Blog: ModelLock: Locking Your Model With a Spell.
- Blog: CATER: Intellectual Property Protection on Text Generation APIs via Conditional Watermarks
- Blog: DOGe: Defensive Output Generation for LLM Protection Against Knowledge Distillation
- Blog: GuardEmb: Dynamic Watermark for Safeguarding Large Language Model Embedding Service Against Model Stealing Attack
- Blog: Increasing the Cost of Model Extraction with Calibrated Proof of Work
- Blog: QUEEN: Query Unlearning against Model Extraction
- Blog: TransLinkGuard: Safeguarding Transformer Models Against Model Stealing in Edge Deployment
- Blog: MOVE: Effective and Harmless Ownership Verification via Embedded External Features
- Blog: REEF: Representation Encoding Fingerprints for Large Language Models
- Blog: Copy, Right? A Testing Framework for Copyright Protection of Deep Learning Models
- Blog: Cybersecurity and AI: The PRALab Research Experience
- Blog: VeriDIP: Verifying Ownership of Deep Neural Networks through Privacy Leakage Fingerprints
- Blog: Bucks for Buckets (B4B): Active Defenses Against Stealing Encoders
- Blog: Model Unmerging: Making Your Models Unmergeable for Secure Model Sharing
- Blog: ATOM: A Framework of Detecting Query-Based Model Extraction Attacks for Graph Neural Networks
- Blog: Ward: Provable RAG Dataset Inference via LLM Watermarks
- Blog: Ward: Provable RAG Dataset Inference via LLM Watermarks
- Blog: ArtistAuditor: Auditing Artist Style Pirate in Text-to-Image Generation Models
- Blog: Poisoning Attacks and Defenses to Federated Unlearning
- Blog: On the Robustness of Dataset Inference
- Blog: Non-transferable Pruning
- Blog: Few-Shot Detection of Machine-Generated Text using Style Representations
- Blog: Intellectual property protection for deep learning model and dataset intelligence
- Blog: Train to Defend: First Defense Against Cryptanalytic Neural Network Parameter Extraction Attacks
- Blog: HoneypotNet: Backdoor Attacks Against Model Extraction
- Blog: RMLM: A Flexible Defense Framework for Proactively Mitigating Word-level Adversarial Attacks
- Blog: How to Trace Latent Generative Model Generated Images without Artificial Watermark?
- Blog: Vision-Language Model IP Protection via Prompt-based Learning
- Blog: Secure Your Model: An Effective Key Prompt Protection Mechanism for Large Language Models
- Blog: GoodDiffusion: Proactive Copyright Protection for Diffusion Bridge Models via Learnable Sample-specific Signatures
- Blog: PATFinger: Prompt-Adapted Transferable Fingerprinting against Unauthorized Multimodal Dataset Usage
- Blog: Defense against Model Extraction Attack by Bayesian Active Watermarking
- Blog: Model Extraction Warning in MLaaS Paradigm
- Blog: PragLocker: Protecting Agent Intellectual Property in Untrusted Deployments via Non-Portable Prompts
- Blog: NNSplitter: An Active Defense Solution for DNN Model via Automated Weight Obfuscation
- Blog: *MemPot*: Defend Against Memory Extraction Attack with Optimized Honeypots
- Blog: Tracking the Copyright of Large Vision-Language Models through Parameter Learning Adversarial Images
- Blog: ActiveDaemon: Unconscious DNN Dormancy and Waking Up via User-specific Invisible Token
- Blog: DeepTaster: Adversarial Perturbation-Based Fingerprinting to Identify Proprietary Dataset Use in Deep Neural Networks
- Blog: Dataset Inference: Ownership Resolution in Machine Learning
- Blog: Perturb Your Data: Paraphrase-Guided Training Data Watermarking
- Blog: Disrupting Model Merging: A Parameter-Level Defense Without Sacrificing Accuracy
- Blog: Misclassification-driven Fingerprinting for DNNs Using Frequency-aware GANs
- Blog: DLP: towards active defense against backdoor attacks with decoupled learning process
- Blog: Silent Guardian: Protecting Text from Malicious Exploitation by Large Language Models
- Blog: AdvMind: Inferring Adversary Intent of Black-Box Attacks
History & citation
Current · Permanent link
- This direction split from Active Defense for Deep Learning Intellectual Property (55% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_passive_defense_limitations_a9e5dd09,
title = {passive defense limitations},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/passive-defense-limitations/rdr_a9e5dd09a4ae4aa9a50b164aaa665907},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-20},
}This exact version (version 1, frozen text):
@misc{lacuna_passive_defense_limitations_a9e5dd09_v1,
title = {passive defense limitations},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/passive-defense-limitations/rdr_a9e5dd09a4ae4aa9a50b164aaa665907/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-20},
}