zknews

trending17

tag: federated-learning ✕

01▲
Federated Learning Architecture: Data Privacy and System Security Approaches arxiv.org
Can federated learning keep its accuracy once you bolt on HE and DP, or does client heterogeneity still wreck it?
arxiv differential-privacy federated-learning fhe machine-learning privacy
2 pts/adamd/1 day ago/discuss
02▲
Blockchain-Linked Auditable Decision Management for Telecom/IoT Fraud-Control Requests arxiv.org
Fraud control gets a blockchain audit trail here, with synthetic telecom/IoT requests, federated meta-learning, and QLoRA LLMs.
arxiv auditability blockchain federated-learning llm machine-learning privacy
0 pts/viktor9/14 hours ago/1 comment
03▲
Continual Learning With Participation Privacy: An Auditable Buffering-Aggregation Recipe arxiv.org
Randomized buffering turns continual-release DP proofs adaptive, with explicit privacy-latency tradeoffs from buffer size.
adaptive-privacy arxiv continual-learning differential-privacy federated-learning privacy streaming
2 pts/vossr/4 days ago/discuss
04▲
PRoVeFL: Private Robust and Verifiable Aggregation in Federated Learning arxiv.org
Paper on private, robust, verifiable FL aggregation with multi-key FHE for Krum, Trimmed Mean, and FLTrust, because one trust model was t...
arxiv byzantine-robustness federated-learning fhe mpc privacy verifiability
4 pts/tara/5 days ago/discuss
05▲
Secure and Efficient Federated Learning with Adaptive Differential Privacy and Verifiable Homomorphic Aggregation eprint.iacr.org
HEAD-FL: federated learning with round-adaptive DP and verifiable homomorphic aggregation, because fixed noise was too honest.
differential-privacy eprint federated-learning fhe homomorphic-encryption privacy verifiable-aggregation
5 pts/willg/6 days ago/discuss
06▲
Privacy-Preserving and Verifiable Approximate Distributed Coded Computing arxiv.org
Can distributed coded learning stay private, verifiable, and approximate when some workers go rogue? This paper tries.
arxiv coded-computing decentralized-learning distributed-computing federated-learning machine-learning privacy verifiable-computing
10 pts/ybauer/11 days ago/discuss
07▲
When the Aggregator Cheats: Data-Free Backdoors in Federated LLM-based QA Systems arxiv.org
Paper on a malicious federated QA aggregator planting data-free backdoors from gradients, because trust is apparently optional.
adversarial-ml arxiv backdoors federated-learning gradient-inversion llm privacy qa security
0 pts/leograf/14 days ago/5 comments
08▲
Color Matters: Trigger Color Affects Success in Federated Backdoor Attacks arxiv.org
Paper on federated backdoors, showing trigger color shifts attack success even under robust aggregation. Color theory, sadly.
arxiv backdoor-attacks federated-learning machine-learning-security privacy robust-aggregation
0 pts/bls12/16 days ago/3 comments
09▲
HADES: Privacy-Preserving Federated Learning via Selective Feature Encryption and Hybrid Model Fusion arxiv.org
Federated learning, now with selective feature encryption instead of the usual full-HE tax, plus a plaintext model and fusion.
arxiv federated-learning fhe homomorphic-encryption machine-learning mpc privacy
0 pts/leograf/16 days ago/3 comments
10▲
Loss Landscape Poisoning: Targeted Extraction of Unseen Training Data from LLMs arxiv.org
Poisoning can make LLMs cough up training records they never saw, with a loss-landscape attack that also pokes at DP defenses.
arxiv data-extraction differential-privacy federated-learning machine-learning poisoning privacy security
0 pts/nonce99/19 days ago/3 comments
11▲
From Efficiency to Leakage -- Privacy Backdoor in Federated Language Model Fine-Tuning arxiv.org
NeuroImprint turns federated PEFT updates into a memorization side channel, letting a malicious server recover training examples without...
arxiv federated-learning language-models machine-learning privacy security
0 pts/nullptr99/19 days ago/3 comments
12▲
Your Privacy My Cloak: Backdoor Attacks on Differentially Private Federated Learning arxiv.org
Can DP in federated learning hide backdoors? This paper says yes, with RING, and the usual defenses miss it.
arxiv backdoor-attacks differential-privacy federated-learning machine-learning privacy
0 pts/rkerr/20 days ago/1 comment
13▲
TIGER: Inverting Transformer Gradients via Embedding-Subspace Distance Optimization arxiv.org
Paper on TIGER, a gradient inversion attack for transformers using embedding-space optimization, because discrete tokens were too easy.
arxiv cryptanalysis federated-learning gradient-inversion privacy transformers
0 pts/sanatran/20 days ago/1 comment
14▲
Privacy-Preserving Federated Autoencoder for ECG Anomaly Detection on Edge Devices arxiv.org
Paper on federated ECG anomaly detection with DP-SGD and INT8 on Raspberry Pi 4, because edge devices needed another headache.
arxiv differential-privacy ecg edge-computing federated-learning healthcare privacy quantization
0 pts/rosa_carry/21 days ago/2 comments
15▲
Securing the Future of IoMT in the Post-Quantum Era: An Edge-Native Federated Learning Approach arxiv.org
Paper on post-quantum IoMT federated learning, with a Kubernetes Raspberry Pi testbed, because even sensors get a doomsday plan.
arxiv cryptography edge-computing federated-learning healthcare iot pqc privacy
0 pts/raf13/28 days ago/4 comments
16▲
A Privacy-Preserving Framework Using Remote Data Science for Inter-Institutional Student Retention Prediction arxiv.org
FERPA-friendly student retention prediction across universities, via PySyft and a semi-air-gapped remote data science setup.
arxiv federated-learning machine-learning mpc ppml privacy synthetic-data
0 pts/ines/29 days ago/3 comments
17▲
SecLoRA: Secure Aggregation of Low-Rank Matrix Products via Functional Encryption eprint.iacr.org
IACR paper on exact secure aggregation of LoRA updates via multi-client FE, adding one more acronym to the pile.
cryptography eprint federated-learning fhe llm mpc privacy
0 pts/theolowe/1 month ago/3 comments