重新思考标签翻转攻击:从样本掩盖到样本值
相关实验视频
Updated: Jul 13, 2025

08:05
Testing Tactile Masking between the Forearms
Published on: February 10, 2016
6.4K
IEEE transactions on pattern analysis and machine intelligence
|October 11, 2023
概括
本研究介绍了样本值,这是一种有效的方法来打击机器学习 (ML) 和深度学习 (DL) 中的标签翻转攻击. 新的算法有效地通过翻转训练数据标签来破坏模型性能,即使是替代模型.
科学领域:
- 人工智能的人工智能
- 机器学习安全 机器学习安全
- 深度学习 (Deep Learning) 是一种深度学习.
背景情况:
- 机器学习 (ML) 和深度学习 (DL) 是人工智能的基础技术.
- 这些方法易受对抗性攻击的影响,构成重大安全风险.
- 标签转换攻击 (LFA) 通过改变训练数据标签来破坏模型.
研究的目的:
- 为了解决现有的深度学习LFA方法的可扩展性限制.
- 提出一个高效和可扩展的算法,用于标签翻转攻击.
- 在对抗性攻击场景中分析替代模型的有效性.
主要方法:
- 重构标签翻转攻击作为一个新的最小值问题.
- 开发样本值算法,以实现有效的样本选择.
- 对于不可预测的受害者模型的替代模型范式的理论分析.
- 将该方法扩展到众包排名任务.
主要成果:
- 样本值允许对深度学习模型进行高效的标签翻转攻击.
- 提出的方法是可扩展的,适用于大型数据集.
- 理论分析表明,与代用模型的性能差距很小.
- 在真实世界数据集上的实验验证证证了该方法的有效性.
结论:
- 样本值为对抗性标签翻转攻击提供了一种有效和可扩展的方法.
- 该方法是强大的和适应性的,即使在代孕模型的存在.
- 这项研究促进了对ML/DL安全威胁的理解和缓解.
相关概念视频
Upsampling
242
Managing signal sampling rates is essential in digital signal processing to maintain signal integrity. A decimated signal, characterized by a reduced frequency range due to its lower sampling rate, can be upsampled by inserting zeros between each sample. This upsampling process expands the original spectrum and introduces repeated spectral replicas at intervals dictated by the new Nyquist frequency. To refine this zero-inserted sequence, it is passed through a lowpass filter with a cutoff...
242
Sampling Theorem
354
In signal processing, the analysis of continuous-time signals, denoted as x(t), often involves sampling techniques to convert these signals into discrete-time signals. This process is essential for digital representation and manipulation. A critical component in sampling is the train of impulses, characterized by the sampling interval and the sampling frequency. The relationship between these parameters and the original signal's properties dictates the success of the sampling process.
354
Sampling Continuous Time Signal
269
In signal processing, a continuous-time signal can be sampled using an impulse-train sampling technique, followed by the zero-order hold method. Impulse-train sampling involves the use of a periodic impulse train, which consists of a series of delta functions spaced at regular intervals determined by the sampling period. When a continuous-time signal is multiplied by this impulse train, it generates impulses with amplitudes corresponding to the signal's values at the sampling points.
In the...
In the...
269
Masking and Demasking Agents
2.5K
EDTA titrations may necessitate masking and demasking agents to temporarily protect a particular metal ion in a mixture from the EDTA reaction. These agents facilitate the sequential analysis of the metal ions by forming stable complexes with some—but not all—metal ions during certain steps.
There are many masking agents, such as cyanide, fluoride, triethanolamine, thiourea, and 2,3-bis(sulfanyl)propan-1-ol (formerly 2,3-dimercapto-1-propanol), with the masking agent chosen based on...
There are many masking agents, such as cyanide, fluoride, triethanolamine, thiourea, and 2,3-bis(sulfanyl)propan-1-ol (formerly 2,3-dimercapto-1-propanol), with the masking agent chosen based on...
2.5K
Sample Handling
106
Transportation of samples from the collection point to the laboratory, as well as storage and preservation techniques, are crucial for maintaining sample integrity and ensuring accurate and reliable test results.
Samples should be transported carefully from collection points to the laboratory. They should be properly sealed and clearly labeled to prevent cross-contamination. To preserve the sample integrity, optimal temperature conditions during transport are essential. This could involve using...
Samples should be transported carefully from collection points to the laboratory. They should be properly sealed and clearly labeled to prevent cross-contamination. To preserve the sample integrity, optimal temperature conditions during transport are essential. This could involve using...
106
Downsampling
167
When considering a sampled sequence with zero values between sampling instants, one can replace it by taking every N-th value of the sequence. At these integer multiples of N, the original and sampled sequences coincide. This process, known as decimation, involves extracting every N-th sample from a sequence, thereby creating a more efficient sequence.
The Fourier transform of the decimated sequence reveals a combination of scaled and shifted versions of the original spectrum. This...
The Fourier transform of the decimated sequence reveals a combination of scaled and shifted versions of the original spectrum. This...
167

