paper-with-me

Papers

MixTailor: Mixed Gradient Aggregation for Robust Learning Against Tailored Attacks

2022-07-16 · Ali Ramezani-Kebrya, Iman Tabrizian, Fartash Faghri, Petar Popovski

Implementations of SGD on distributed systems create new vulnerabilities, which can be identified and misused by one or more adversarial agents. Recently, it has been shown that well-known Byzantine-resilient gradient aggregation schemes are indeed vulnerable to informed attackers that can tailor the attacks (Fang et al., 2020; Xie et al., 2020b). We introduce MixTailor, a scheme based on randomization of the aggregation strategies that makes it impossible for the attacker to be fully informed. Deterministic schemes can be integrated into MixTailor on the fly without introducing any additional hyperparameters. Randomization decreases the capability of a powerful adversary to tailor its attacks, while the resulting randomized aggregation scheme is still competitive in terms of performance. For both iid and non-iid settings, we establish almost sure convergence guarantees that are both stronger and more general than those available in the literature. Our empirical studies across various datasets, attacks, and settings, validate our hypothesis and show that MixTailor successfully defends when well-known Byzantine-tolerant schemes fail.

📄 PDF Abstract BibTeX arXiv:2207.07941

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

SGD Stochastic Gradient Descent is an iterative optimization technique that uses minibatches of data to form an expectation of the gradient, rather than the full gradient using…

Similar Papers 제목 키워드 기반

MixNN: Protection of Federated Learning Against Inference Attacks by Mixing Neural Network Layers

2021-09-26 · Antoine Boutet, Thomas Lebrun, Jan Aalmoes, Adrien Baud

Machine Learning (ML) has emerged as a core technology to provide learning models to perform complex tasks. Boosted by Machine Learning as a Service (MLaaS), the number of applications relying on ML capabilities is ever …

AttributeFederated LearningInference AttackPrivacy Preserving

Encoded Gradients Aggregation against Gradient Leakage in Federated Learning

2022-05-26 · Dun Zeng, Shiyu Liu, Siqi Liang, Zonghang Li 외

Federated learning enables isolated clients to train a shared model collaboratively by aggregating the locally-computed gradient updates. However, privacy information could be leaked from uploaded gradients and be expose…

Federated Learning

G-FARS: Gradient-Field-based Auto-Regressive Sampling for 3D Part Grouping

2024-05-10 · CVPR 2024 1 · Junfeng Cheng, Tania Stathaki

This paper proposes a novel task named "3D part grouping". Suppose there is a mixed set containing scattered parts from various shapes. This task requires algorithms to find out every possible combination among all the p…

Graph Neural Network

SFT-then-RL Outperforms Mixed-Policy Methods for LLM Reasoning

2026-04-26 · Alexis Limozin, Eduard Durech, Torsten Hoefler, Imanol Schlag 외 arxiv

Recent mixed-policy optimization methods for LLM reasoning that interleave or blend supervised and reinforcement learning signals report improvements over the standard SFT-then-RL pipeline. We show that numerous recently…

Reinforcement Learning

Reveal Your Images: Gradient Leakage Attack against Unbiased Sampling-Based Secure Aggregation

2023-04-28 · IEEE Transactions on Knowledge and Data Engineering 2023 4 · Y Yang, Z Ma, B Xiao, Y Liu 외

Recently, some Unbiased Gradient Sampling-based (UGS) methods are proposed to mitigate gradient leakage by introducing sampling and unbiased transformation, such as MinMax Sampling in SIGMOD '22. In this paper, we first …

Federated Learning