arXiv Machine Learning
PassGPT+: Leveraging Linguistic Priors for Password Modeling
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv AI
Aug 7
One Leak Away: How Pretrained Model Exposure Amplifies Jailbreak Risks in Finetuned LLMs
arXiv:2512. 14751v3 Announce Type: replace-cross Abstract: Finetuning pretrained large language models (LLMs) has become the standard paradigm for developing downstream applications.
arXiv Machine Learning
Aug 14
A Prior-Aware Metric for Efficiently Distinguishing Memorization from Generalization in Large Language Models
arXiv:2602. 18733v2 Announce Type: replace Abstract: Training data leakage from Large Language Models (LLMs) raises serious concerns related to privacy, security, and copyright compliance.
arXiv Machine Learning
Sep 22
Probe-Geometry Alignment: Erasing the Cross-Sequence Memorization Signature Below Chance
arXiv:2605.01699v4 Announce Type: replace Abstract: Recent attacks show that behavioural unlearning of large language models leaves internal traces recoverable by adversarial probes. We characterise...
arXiv Machine Learning
Aug 27
Reconstruction of Personally Identifiable Information from Proprietary Data in Supervised Fine-Tuned Models
The paper examines how supervised fine-tuning (SFT) of large language models can leak personally identifiable information (PII) when the fine-tuning data contains user-provided sensitive details. It introduces COVA, a coverage-aware decoding algorithm that improves targeted PII reconstruction from SFT models, especially when an adversary has limited contextual knowledge about a target. Experiments on medical and legal Q&A datasets show that even small proprietary SFT datasets can lead to significant privacy leakage via PII reconstruction.
arXiv Machine Learning
4d ago
Do LLMs Really Forget? Hidden-State Leakage in Model Unlearning and How to Fix it
arXiv:2609.36612v1 Announce Type: new Abstract: Unlearning in large language models (LLMs) is typically evaluated at the output level, where a model appears to suppress sensitive or undesirable conte...
arXiv AI
Jun 16
SPARK: Security Knowledge Priming and Representation-Guided Knowledge Activation for LLM-based Secure Code Generation
arXiv:2606. 16244v1 Announce Type: cross Abstract: Large language models routinely generate code with exploitable security flaws.