ReTokSync resolves tokenization ambiguity in generative linguistic steganography via targeted self-synchronizing resets, achieving over 99.7% extraction accuracy and 100% recovery with an auxiliary channel while matching baseline security and quality.
Title resolution pending
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
other 1
citation-polarity summary
verdicts
UNVERDICTED 5roles
other 1polarities
unclear 1representative citing papers
JECA^2 is a new white-box attack method using Grad-CAM-guided perturbations and prompt embedding optimization to achieve judgment-explanation consistent adversarial attacks on forensic VLMs.
Introduces Grouped Memorization Evaluation and FedMemPrune to remove unique memorized information in federated unlearning while preserving overlapping knowledge.
SISA training lets RL ransomware detectors forget selected samples by retraining one shard, with under 0.05% F1 drop and much lower retraining cost than full retraining.
Applies Matrix Profiles for time-series outlier detection and graph-based anomaly detection to identify intrusions in operational industrial networks on labeled experimental and emulated datasets.
citing papers explorer
-
ReTokSync: Self-Synchronizing Tokenization Disambiguation for Generative Linguistic Steganography
ReTokSync resolves tokenization ambiguity in generative linguistic steganography via targeted self-synchronizing resets, achieving over 99.7% extraction accuracy and 100% recovery with an auxiliary channel while matching baseline security and quality.
-
JECA^2: Judgment-Explanation Consistent Adversarial Attack against Forensic Vision-Language Models
JECA^2 is a new white-box attack method using Grad-CAM-guided perturbations and prompt embedding optimization to achieve judgment-explanation consistent adversarial attacks on forensic VLMs.
-
Rethinking Federated Unlearning via the Lens of Memorization
Introduces Grouped Memorization Evaluation and FedMemPrune to remove unique memorized information in federated unlearning while preserving overlapping knowledge.
-
Privacy-Aware Machine Unlearning with SISA for Reinforcement Learning-Based Ransomware Detection
SISA training lets RL ransomware detectors forget selected samples by retraining one shard, with under 0.05% F1 drop and much lower retraining cost than full retraining.
-
Using Temporal and Topological Features for Intrusion Detection in Operational Networks
Applies Matrix Profiles for time-series outlier detection and graph-based anomaly detection to identify intrusions in operational industrial networks on labeled experimental and emulated datasets.