arXiv AI
Aug 17
CutClean: Neural Network Pruning for Privacy-Preserving Inference
arXiv:2608. 13773v1 Announce Type: cross Abstract: Neural networks are increasingly deployed in high-stakes applications with growing privacy leakage concerns.
Prune the Leaky Neurons: Mitigating Private Data Leakage in Fine-Tuned LLMs via Joint-Embedding-Guided Pruning
The paper introduces JEPA‑Prune, a post‑hoc neuron‑pruning method that mitigates private data leakage in fine‑tuned large language models. It trains a public model on PII‑free surrogate views using a joint‑embedding predictive architecture, then uses cross‑model representation probes, integrated gradients, and a specificity score to identify and prune neurons that respond to personally identifiable information. Experiments show that pruning only 1.6% of neurons can dramatically reduce PII inference accuracy and recall while preserving model utility, outperforming existing privacy‑neuron editing techniques.
Related stories
arXiv AI
Aug 25
Reinforcement Learning on Benign Facts Amplifies Leakage of Memorized Private Data
arXiv:2608.21727v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards (RLVR) is deployed to make models better at reasoning tasks, but its side effect on what models will d...
arXiv Machine Learning
Jul 16
When T2I Synthetic Data Backfires: Amplified Privacy Risks in Real-Synthetic Mix Training
arXiv:2607. 13541v1 Announce Type: cross Abstract: To overcome data scarcity and privacy constraints in data collection, it has become standard practice across academia and industry to augment real training data with text-to-image (T2I)-generated synthetic data, a paradigm we term Real-Synthetic Mix-Training (RSMT).
arXiv AI
Sep 25
Decoupling Knowledge and Privacy: Post-Task Self-Distillation Replay for LLM Continual Learning
The paper introduces SPARK, a method for privacy‑preserving continual learning that decouples knowledge retention from privacy correction. SPARK freezes the post‑task distribution and then selectively corrects it to reduce the likelihood of sensitive content while maintaining strong performance on current and past tasks. Experiments show that this approach effectively suppresses PII and preserves continual‑learning utility across various settings.
arXiv Machine Learning
Jun 5
SHRED: Retain-Set-Free Unlearning via Self-Distillation with Logit Demotion
arXiv:2605. 07482v2 Announce Type: replace Abstract: Machine unlearning for large language models (LLMs) aims to selectively remove memorized content such as private data, copyrighted text, or hazardous knowledge, without costly full retraining.
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
Jul 31
TriShield: Zero-Utility-Loss Defense Against Privacy Backdoors in Federated Language Model Fine-Tuning via Orthogonal Gradient Projection and Optimizer State Entanglement
arXiv:2607. 27940v1 Announce Type: new Abstract: Federated fine-tuning of large language models (LLMs) enables collaborative training without exposing raw data.
arXiv Machine Learning
Oct 8
Efficient Provably Private Classification with a Tabular Foundation Model
Efficient Provably Private Classification with a Tabular Foundation Model introduces PrivTab, a tabular foundation model that embeds differential privacy directly into its architecture. Pretrained on simulated datasets, PrivTab uses in-context learning to convert sensitive rows into compact, provably private summaries, enabling a single forward pass for classification. The model outperforms private linear and neural‑network baselines under moderate-to-strong privacy, shows negligible membership leakage, maintains well‑calibrated predictions, and reduces dataset fitting time by 10,000×.
Hugging Face Trending Papers
Sep 9
Forgetting Only What Matters: Layer-Selective Unlearning toward Robust LLMs
Large Language Models (LLMs) can memorize and reproduce sensitive, copyrighted, or otherwise undesirable training content, creating privacy, safety, and regulatory concerns. Machine unlearning offers...
arXiv AI
Oct 12
DP-MIND: Differentially private memory-guided Long context Inference
DP-MIND is a memory‑guided framework that enables differentially private inference for large language models on million‑token contexts. It locally perturbs user queries and processes them in chunks, using a compact memory that retains task‑relevant information across the sequence. The memory construction is optimized via reinforcement learning on perturbed inputs, and a local denoising module recovers corrupted answer spans, resulting in improved scalability and utility over existing DP and long‑context inference baselines.
arXiv Computation and Language
6d ago
Exploring The Empirical Privacy Landscape of Synthetic Data
The paper compares data-level and training-level methods for balancing language model capability and privacy leakage on synthetic medical records with embedded canaries. Direct finetuning achieves the highest capability but leaks the most private information, while DP‑SGD reduces leakage at a significant cost to performance. Generating privacy‑aware synthetic data—especially with uniqueness‑aware rewriting—offers a better trade‑off, and more capable rewriting models tend to lower downstream privacy risks, though gains are inconsistent with increased compute.
arXiv AI
Sep 11
Forgetting Only What Matters: Layer-Selective Unlearning toward Robust LLMs
The paper introduces Forgetting Only What Matters via Unlearning Layers (FOM-UL), a layer‑selective unlearning framework for large language models. FOM-UL uses a forget‑to‑retain significance score to identify transformer layers that strongly influence the forget set while being insensitive to the retain set, allowing targeted updates that preserve most of the model. Experiments on TOFU, KnowUnDo, and MUSE-style benchmarks show that FOM-UL reduces residual memorization and maintains utility better than several baselines, even after 8‑bit and 4‑bit post‑training quantization, and it also limits recovery of forgotten content in adversarial prompt tests.