REVIEW 28 cited by
iDLG: Improved Deep Leakage from Gradients
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
iDLG: Improved Deep Leakage from Gradients
read the original abstract
It is widely believed that sharing gradients will not leak private training data in distributed learning systems such as Collaborative Learning and Federated Learning, etc. Recently, Zhu et al. presented an approach which shows the possibility to obtain private training data from the publicly shared gradients. In their Deep Leakage from Gradient (DLG) method, they synthesize the dummy data and corresponding labels with the supervision of shared gradients. However, DLG has difficulty in convergence and discovering the ground-truth labels consistently. In this paper, we find that sharing gradients definitely leaks the ground-truth labels. We propose a simple but reliable approach to extract accurate data from the gradients. Particularly, our approach can certainly extract the ground-truth labels as opposed to DLG, hence we name it Improved DLG (iDLG). Our approach is valid for any differentiable model trained with cross-entropy loss over one-hot labels. We mathematically illustrate how our method can extract ground-truth labels from the gradients and empirically demonstrate the advantages over DLG.
Forward citations
Cited by 28 Pith papers
-
From Efficiency to Leakage -- Privacy Backdoor in Federated Language Model Fine-Tuning
NeuroImprint attack assigns isolated memorization neurons to training samples in PEFT adapters, enabling closed-form reconstruction of 59-79% of samples across BERT, GPT-2, Qwen2, and Llama3.2 on multiple datasets.
-
TIGER: Inverting Transformer Gradients via Embedding-Subspace Distance Optimization
TIGER turns the low-rank attention gradient subspace into a differentiable objective for continuous embedding optimization, improving reconstruction quality and robustness over prior discrete token tests especially un...
-
Loss Landscape Poisoning: Targeted Extraction of Unseen Training Data from LLMs
Poisoning training data reshapes the loss landscape to enable targeted extraction of unseen data from LLMs with high success rates in language and vision-language models.
-
TriShield: Zero-Utility-Loss Defense Against Privacy Backdoors in Federated Language Model Fine-Tuning via Orthogonal Gradient Projection and Optimizer State Entanglement
TriShield combines artifact detection, Adam momentum pre-entanglement, and SVD task-subspace projection to drive NeuroImprint reconstruction to 0% with claimed near-zero utility loss.
-
BettiSplit: Topology-Guided Privacy-Aware Split Learning Against Feature Inversion and Gradient Leakage
Persistent Betti-1 of smashed activations is proposed as an attack-free indicator of feature-inversion risk in split learning, used for split selection and regularization.
-
FedCVESA: Taking Away Training Data in Federated Learning via Correlation Value Encoding and Segmented Aggregation
A malicious FL server can steal private training images by encoding them into model parameters via a correlation regularizer and preserving them through segmented aggregation.
-
TL++: Accuracy and Privacy Preserving Traversal Learning for Distributed Intelligent Systems
TL++ recovers centralized mini-batch gradients via virtual batches in split learning and adds secret sharing for cut-layer tensors, achieving 91.41% accuracy on CIFAR-10 with 13x lower communication than full-model sync.
-
Exposing the Illusion of Erasure in Knowledge Editing for LLMs
Knowledge editing methods redistribute and suppress rather than overwrite facts in LLMs, creating narrow vulnerable regions in representation space that adversarial prompts can exploit.
-
HADES: Privacy-Preserving Federated Learning via Selective Feature Encryption and Hybrid Model Fusion
HADES selectively encrypts privacy-sensitive features identified by PCA in federated learning, trains hybrid encrypted and plaintext networks, and fuses them to match vanilla FL accuracy with reduced overhead and bett...
-
Secure Aggregation with Top-K Sparsification in Decentralized Federated Learning
A sparse secure aggregation scheme for decentralized federated learning that supports top-K sparsification, user dropouts, and collusion while preserving model accuracy at 1% sparsity.
-
Local Differential Privacy via Dynamic Quantization in Distributed Online Stochastic Optimization
Dynamic quantization provides local differential privacy in distributed online stochastic optimization with almost sure convergence on directed graphs.
-
Response-Conditioned Parallel-to-Sequential Orchestration for Multi-Agent Systems
Nexa learns a response-conditioned policy that starts with parallel agent execution and adds at most one round of sequential message passing via a predicted sparse DAG, strictly subsuming pure parallel mode.
-
On What We Can Learn from Low-Resolution Data
Low-resolution data improves high-resolution model performance when high-resolution samples are limited, via KL-divergence bounds and experiments on vision transformers and CNNs.
-
Federated User Behavior Modeling for Privacy-Preserving LLM Recommendation
SF-UBM enables privacy-preserving cross-domain LLM recommendation by federating semantic item representations, distilling domain knowledge, and aligning preferences into LLM soft prompts.
-
Approximate and Weighted Data Reconstruction Attack in Federated Learning
An interpolation approximation plus layer-weighted loss enables stronger data reconstruction attacks on FedAvg federated learning, with experiments showing gains on image data over prior methods.
-
Privacy Leakage in Federated Learning in Radiology Reports: A Comparative Evaluation of Tokenizer-Driven Privacy Risks
Up to 44% of radiology report sentences were exactly reconstructed from federated-learning gradients in this worst-case attack, with the RadBERT tokenizer leaking the most—but the paper's own re-run did not reproduce ...
-
Profiling Privacy Preservation Against Gradient Inversion Attacks in Tabular Federated Learning
Empirical study finds small client batches most vulnerable to gradient inversion in tabular FL, FT-Transformer harder to invert than MLP baselines, and aggregate accuracy metrics can overstate exact record recovery.
-
FIRMA: FIbonacci Ring Model Aggregation for Privacy-preserving Federated Learning
FIRMA introduces Fibonacci ring aggregation protocols for server-free federated learning that maintain private heads and achieve higher accuracy than FedAvg under label skew across multiple benchmarks and heterogeneit...
-
LightSplit: Practical Privacy-Preserving Split Learning via Orthogonal Projections
LightSplit uses non-invertible orthogonal projections as an information bottleneck in split learning to reduce transmitted dimensionality by 32x while retaining more than 95% accuracy and limiting reconstruction risk.
-
UMEDA: Unified Multi-modal Efficient Data Fusion for Privacy-Preserving Graph Federated Learning via Spectral-Gated Attention and Diffusion-Based Operator Alignment
UMEDA is a new graph federated learning method that uses low-rank spectral filtering and diffusion over a shared integral operator to fuse multi-modal data privately, outperforming baselines on MM-Fi and RELI11D under...
-
Scalable and Private Federated Learning Using Distributed Differential Privacy and Secure Aggregation
A blacklist/whitelist-guided prompt optimization plus diffusion pipeline produces de-identified chest X-rays that retain enough pathology for competitive report-generation training while cutting patient-identity class...
-
Scalable and Private Federated Learning Using Distributed Differential Privacy and Secure Aggregation
DDP-SA combines client-side Laplace noise perturbation with full-threshold additive secret sharing to let federated learning servers reconstruct only aggregated noisy gradients without exposing individual client updates.
-
FedSpy-LLM: Towards Scalable and Generalizable Data Reconstruction Attacks from Gradients on LLMs
FedSpy-LLM uses gradient decomposition and iterative alignment to reconstruct larger batches and longer sequences of training data from LLM gradients in federated settings, including with PEFT methods.
-
Don't Trust the AI Ecosystem: Analyzing Privacy Leakage in Compromised Open-Source Components
An attacker who controls a training script can store exact copies of private images inside model weights and extract them losslessly after training.
-
DPDL: Towards Differential Privacy Preservation in Decentralized Stochastic Learning on Non-IID Data
DPDL perturbs cross-gradients with Gaussian noise for DP and applies cosine similarity calibration to support linear speedup in decentralized training on non-IID data.
-
SafeLM: Unified Privacy-Aware Optimization for Trustworthy Federated Large Language Models
SafeLM unifies privacy-preserving federated LLM training with Paillier encryption, attack defenses, contrastive grounding, and binarized aggregation to achieve 98% harmful content detection, 96.9% less communication, ...
-
Code-Poisoning Property Inference Attacks
Code-level access lets CPPIA copy dataset proportions into the model's architecture as a hardcoded backdoor, so the 'inference' is just decoding what the attacker already computed.
-
Knowledge Distillation in Federated Learning: a Survey on Long Lasting Challenges and New Solutions
A survey organizing knowledge distillation techniques for addressing privacy, heterogeneity, communication, and personalization challenges in federated learning.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.