中文
相关论文

相关论文: Confidential Guardian: Cryptographically Prohibiti…

200 篇论文

Machine learning (ML) systems are increasingly deployed in high-stakes domains where reliability is paramount. This thesis investigates how uncertainty estimation can enhance the safety and trustworthiness of ML, focusing on selective…

机器学习 · 计算机科学 2025-09-09 Stephan Rabanser

Model stealing attack is increasingly threatening the confidentiality of machine learning models deployed in the cloud. Recent studies reveal that adversaries can exploit data synthesis techniques to steal machine learning models even in…

密码学与安全 · 计算机科学 2025-03-25 Yunfei Yang , Xiaojun Chen , Yuexin Xuan , Zhendong Zhao

As privacy concerns escalate in the realm of machine learning, data owners now have the option to utilize machine unlearning to remove their data from machine learning models, following recent legislation. To enhance transparency in machine…

机器学习 · 计算机科学 2026-04-23 Binchi Zhang , Zihan Chen , Cong Shen , Jundong Li

Uncertainty in artificial intelligence (AI) predictions poses urgent legal and ethical challenges for AI-assisted decision-making. We examine two algorithmic interventions that act as guardrails for human-AI collaboration: selective…

计算机与社会 · 计算机科学 2025-08-12 Holli Sargeant , Mackenzie Jorgensen , Arina Shah , Adrian Weller , Umang Bhatt

Being cautious is crucial for enhancing the trustworthiness of machine learning systems integrated into decision-making pipelines. Although calibrated probabilities help in optimal decision-making, perfect calibration remains unattainable,…

机器学习 · 计算机科学 2024-08-12 Mari-Liis Allikivi , Joonas Järve , Meelis Kull

In learning problems, the noise inherent to the task at hand hinders the possibility to infer without a certain degree of uncertainty. Quantifying this uncertainty, regardless of its wide use, assumes high relevance for security-sensitive…

Privacy concerns have led to the development of privacy-preserving approaches for learning models from sensitive data. Yet, in practice, even models learned with privacy guarantees can inadvertently memorize unique training examples or leak…

机器学习 · 统计学 2019-11-11 Mario Diaz , Peter Kairouz , Jiachun Liao , Lalitha Sankar

Adversarial examples crafted by an explicit adversary have attracted significant attention in machine learning. However, the security risk posed by a potential false friend has been largely overlooked. In this paper, we unveil the threat of…

机器学习 · 计算机科学 2021-12-14 Lue Tao , Lei Feng , Jinfeng Yi , Songcan Chen

Machine unlearning offers a practical alternative to avoid full model re-training by approximately removing the influence of specific user data. While existing methods certify unlearning via statistical indistinguishability from re-trained…

机器学习 · 计算机科学 2026-02-02 Hsiang Hsu , Pradeep Niroula , Zichang He , Ivan Brugere , Freddy Lecue , Chun-Fu Chen

Uncertainty quantification is a key pillar of trustworthy machine learning. It enables safe reactions under unsafe inputs, like predicting only when the machine learning model detects sufficient evidence, discarding anomalous data, or…

机器学习 · 计算机科学 2024-08-27 Michael Kirchhof

Machine learning models are prone to memorizing sensitive data, making them vulnerable to membership inference attacks in which an adversary aims to guess if an input sample was used to train the model. In this paper, we show that prior…

密码学与安全 · 计算机科学 2020-12-10 Liwei Song , Prateek Mittal

As machine learning becomes a more mainstream technology, the objective for governments and public sectors is to harness the power of machine learning to advance their mission by revolutionizing public services. Motivational government use…

密码学与安全 · 计算机科学 2020-10-13 Nader Sehatbakhsh , Ellie Daw , Onur Savas , Amin Hassanzadeh , Ian McCulloh

Training reliable deep learning models which avoid making overconfident but incorrect predictions is a longstanding challenge. This challenge is further exacerbated when learning has to be differentially private: protection provided to…

机器学习 · 计算机科学 2023-05-31 Stephan Rabanser , Anvith Thudi , Abhradeep Thakurta , Krishnamurthy Dvijotham , Nicolas Papernot

Gaze estimation models are widely used in applications such as driver attention monitoring and human-computer interaction. While many methods for gaze estimation exist, they rely heavily on data-hungry deep learning to achieve high…

计算机视觉与模式识别 · 计算机科学 2025-02-28 Lingyu Du , Yupei Liu , Jinyuan Jia , Guohao Lan

Despite remarkable progress made in natural language processing, even the state-of-the-art models often make incorrect predictions. Such predictions hamper the reliability of systems and limit their widespread adoption in real-world…

计算与语言 · 计算机科学 2023-05-04 Neeraj Varshney , Chitta Baral

With the ever-growing data and the need for developing powerful machine learning models, data owners increasingly depend on various untrusted platforms (e.g., public clouds, edges, and machine learning service providers) for scalable…

机器学习 · 计算机科学 2021-06-15 Sagar Sharma , Keke Chen

When language models lack relevant knowledge for a given query, they frequently generate plausible responses that can be hallucinations, rather than admitting being agnostic about the answer. Retraining models to reward admitting ignorance…

计算与语言 · 计算机科学 2026-05-01 Rui Xu , Yi Chen , Sihong Xie , Hui Xiong

In a membership inference attack, an attacker aims to infer whether a data sample is in a target classifier's training dataset or not. Specifically, given a black-box access to the target classifier, the attacker trains a binary classifier,…

密码学与安全 · 计算机科学 2019-12-20 Jinyuan Jia , Ahmed Salem , Michael Backes , Yang Zhang , Neil Zhenqiang Gong

Edge-cloud collaborative inference empowers resource-limited IoT devices to support deep learning applications without disclosing their raw data to the cloud server, thus preserving privacy. Nevertheless, prior research has shown that…

密码学与安全 · 计算机科学 2023-06-16 Lin Duan , Jingwei Sun , Yiran Chen , Maria Gorlatova

Machine learning models are vulnerable to adversarial examples: minor perturbations to input samples intended to deliberately cause misclassification. While an obvious security threat, adversarial examples yield as well insights about the…

密码学与安全 · 计算机科学 2019-11-19 Kathrin Grosse , David Pfaff , Michael Thomas Smith , Michael Backes
‹ 上一页 1 2 3 10 下一页 ›