No article text was recorded for this version.
target class identification
Version 1 of 129 papers46 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Reverse Engineering Imperceptible Backdoor Attacks on Deep Neural Networks for Detection and Training Set Cleansing
- Blog: Detection of Backdoors in Trained Classifiers Without Access to the Training Set
- Blog: Universal Soldier: Using Universal Adversarial Perturbations for Detecting Backdoor Attacks
- Blog: AEVA: Black-box Backdoor Detection Using Adversarial Extreme Value Analysis
- Blog: Detect and Remove Watermark in Deep Neural Networks via Generative Adversarial Networks
- Blog: SSL-Cleanse: Trojan Detection and Mitigation in Self-Supervised Learning
- Blog: Detecting Backdoor Attacks Against Point Cloud Classifiers
- Blog: Practical Detection of Trojan Neural Networks: Data-Limited and Data-Free Cases
- Blog: DeepInspect: A Black-box Trojan Detection and Mitigation Framework for Deep Neural Networks
- Blog: Robust Backdoor Removal by Reconstructing Trigger-Activated Changes in Latent Representation
- Blog: A Unified Detection Framework for Inference-Stage Backdoor Defenses
- Blog: Towards Robustness Certification Against Universal Perturbations
- Blog: CBD: A Certified Backdoor Detector Based on Local Dominant Probability
- Blog: Energy-based Backdoor Defense without Task-Specific Samples and Model Retraining
- Blog: L-RED: Efficient Post-Training Detection of Imperceptible Backdoor Attacks without Access to the Training Set
- Blog: Backdoor Attacks on Pre-trained Models by Layerwise Weight Poisoning
- Blog: Revealing Backdoors, Post-Training, in DNN Classifiers via Novel Inference on Optimized Perturbations Inducing Group Misclassification
- Blog: Inspecting Prediction Confidence for Detecting Black-Box Backdoor Attacks
- Blog: SleeperNets: Universal Backdoor Poisoning Attacks Against Reinforcement Learning Agents
- Blog: Black-box Detection of Backdoor Attacks with Limited Information and Data
- Blog: Poisoning and Backdooring Contrastive Learning
- Blog: TERD: A Unified Framework for Safeguarding Diffusion Models Against Backdoors
- Blog: Attack as Defense: Characterizing Adversarial Examples using Robustness
- Blog: FreeEagle: Detecting Complex Neural Trojans in Data-Free Cases
- Blog: MM-BD: Post-Training Detection of Backdoor Attacks with Arbitrary Backdoor Pattern Types Using a Maximum Margin Statistic
- Blog: Post-Training Detection of Backdoor Attacks for Two-Class and Multi-Attack Scenarios
- Blog: Odyssey: Creation, Analysis and Detection of Trojan Models
- Blog: Single Image Backdoor Inversion via Robust Smoothed Classifiers
- Blog: Cassandra: Detecting Trojaned Networks From Adversarial Perturbations
History & citation
Current · Permanent link
Cite this direction
Latest version (a living page):
@misc{lacuna_target_class_identification_ff773d94,
title = {target class identification},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/target-class-identification/rdr_ff773d94c9f9437b81a74c48fe97944a},
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_target_class_identification_ff773d94_v1,
title = {target class identification},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/target-class-identification/rdr_ff773d94c9f9437b81a74c48fe97944a/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-20},
}