No article text was recorded for this version.
clean-label poisoning
Version 2 of 2207 papers280 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Clean-image Backdoor: Attacking Multi-label Models with Poisoned Labels Only
- Blog: BadHash: Invisible Backdoor Attacks against Deep Hashing with Clean Label
- Blog: Learning under $p$-Tampering Attacks
- Blog: Poisoning Language Models During Instruction Tuning
- Blog: Backdoor Attack against Object Detection with Clean Annotation
- Blog: Textual Backdoor Attacks with Iterative Trigger Injection
- Blog: BAAT: Towards Sample-specific Backdoor Attack with Clean Labels
- Blog: Poison Frogs! Targeted Clean-Label Poisoning Attacks on Neural Networks
- Blog: On the Exploitability of Instruction Tuning
- Blog: Does Few-shot Learning Suffer from Backdoor Attacks?
- Blog: Backdoor Attacks and Defenses in Computer Vision Domain: A Survey
- Blog: BadTrack: A Poison-Only Backdoor Attack on Visual Object Tracking
- Blog: Hidden Trigger Backdoor Attacks
- Blog: Prompt as Triggers for Backdoor Attack: Examining the Vulnerability in Language Models
- Blog: VDC: Versatile Data Cleanser based on Visual-Linguistic Inconsistency by Multimodal Large Language Models
- Blog: Backdoor Defense via Deconfounded Representation Learning
- Blog: Poisoning Network Flow Classifiers
- Blog: Poison Frogs! Targeted Clean-Label Poisoning Attacks on Neural Networks
- Blog: Clean-Label Graph Backdoor Attack in the Node Classification Task
- Blog: Untargeted Backdoor Attack against Object Detection
- Blog: Shortcuts Arising from Contrast: Towards Effective and Lightweight Clean-Label Attacks in Prompt-Based Learning
- Blog: Stealthy Yet Effective: Distribution-Preserving Backdoor Attacks on Graph Classification
- Blog: Attacking by Aligning: Clean-Label Backdoor Attacks on Object Detection
- Blog: Stealthy Yet Effective: Distribution-Preserving Backdoor Attacks on Graph Classification
- Blog: Poisoned Forgery Face: Towards Backdoor Attacks on Face Forgery Detection
- Blog: Adversarial Clean Label Backdoor Attacks and Defenses on Text Classification Systems
- Blog: CBV: Clean-label Backdoor Attacks on Vision Language Models via Diffusion Models
- Blog: Hidden Poison: Machine Unlearning Enables Camouflaged Poisoning Attacks
- Blog: Going In Style: Audio Backdoors Through Stylistic Transformations
- Blog: Research on Hidden Backdoor Prompt Attack Method
- Blog: Dataset Security for Machine Learning: Data Poisoning, Backdoor Attacks, and Defenses
- Blog: Machine Learning Security Against Data Poisoning: Are We There Yet?
- Blog: Hidden Poison: Machine Unlearning Enables Camouflaged Poisoning Attacks
- Blog: Label-Consistent Backdoor Attacks
- Blog: Explanation-Guided Backdoor Poisoning Attacks Against Malware Classifiers
- Blog: Backdoor Attack on Hash-based Image Retrieval via Clean-label Data Poisoning
- Blog: Clean-label Backdoor Attack against Deep Hashing based Retrieval
- Blog: Robust learning under clean-label attack
- Blog: Deep k-NN Defense Against Clean-Label Data Poisoning Attacks
- Blog: Did You Train on My Dataset? Towards Public Dataset Protection with Clean-Label Backdoor Watermarking
- Blog: BadReward: Clean-Label Poisoning of Reward Models in Text-to-Image RLHF
- Blog: Triggerless Backdoor Attack for NLP Tasks with Clean Labels
- Blog: Professor X: Manipulating EEG BCI with Invisible and Robust Backdoor Attack
- Blog: Clean Image May be Dangerous: Data Poisoning Attacks Against Deep Hashing
- Blog: WeDef: Weakly Supervised Backdoor Defense for Text Classification
- Blog: Can Adversarially Robust Learning LeverageComputational Hardness?
- Blog: Towards Physical World Backdoor Attacks Against Skeleton Action Recognition
- Blog: Shortcuts Arising from Contrast: Effective and Covert Clean-Label Attacks in Prompt-Based Learning
- Blog: Practical Poisoning Attacks on Neural Networks
- Blog: Data Poisoning in Deep Learning: A Survey
- Blog: Robust Watermarking of Neural Network with Exponential Weighting
- Blog: Witches' Brew: Industrial Scale Data Poisoning via Gradient Matching
- Blog: Selection-Based Vulnerabilities: Clean-Label Backdoor Attacks in Active Learning
- Blog: WeDef: Weakly Supervised Backdoor Defense for Text Classification
- Blog: BadSAD: Clean-Label Backdoor Attacks against Deep Semi-Supervised Anomaly Detection
- Blog: Label Poisoning is All You Need
- Blog: Reflection Backdoor: A Natural Backdoor Attack on Deep Neural Networks
- Blog: A temporal chrominance trigger for clean-label backdoor attack against anti-spoof rebroadcast detection
- Blog: Imperceptible and Multi-channel Backdoor Attack against Deep Neural Networks
- Blog: Obliviousness Makes Poisoning Adversaries Weaker
Showing 60 of 207 papers.
History & citation
Current · Permanent link
Cite this direction
Latest version (a living page):
@misc{lacuna_clean_label_poisoning_3ebccc1d,
title = {clean-label poisoning},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/clean-label-poisoning/rdr_3ebccc1dffdd43bb91ea73eba45b4940},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-20},
}This exact version (version 2, frozen text):
@misc{lacuna_clean_label_poisoning_3ebccc1d_v2,
title = {clean-label poisoning},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/clean-label-poisoning/rdr_3ebccc1dffdd43bb91ea73eba45b4940/v/2},
note = {Version 2, frozen 2026-10-04. Accessed 2026-11-20},
}