相关论文: The Effect of Instruction Padding on SFI Overhead

Federated Instruction Tuning (FIT) has shown the ability to achieve collaborative model instruction tuning among massive data owners without sharing private data. However, it still faces two key challenges, i.e., data and resource…

Spectre attacks and their many subsequent variants are a new vulnerability class affecting modern CPUs. The attacks rely on the ability to misguide speculative execution, generally by exploiting the branch prediction structures, to execute…

The decentralized Federated Learning (FL) setting avoids the role of a potentially unreliable or untrustworthy central host by utilizing groups of clients to collaboratively train a model via localized training and model/gradient sharing.…

Operating Systems enforce logical isolation using abstractions such as processes, containers, and isolation technologies to protect a system from malicious or buggy code. In this paper, we show new types of side channels through the file…

Modern distributed storage systems come with aplethora of configurable parameters that controlmodule behavior and affect system performance. Default settings provided by developers are often suboptimal for specific user cases. Tuning…

Fault attacks enable adversaries to manipulate the control-flow of security-critical applications. By inducing targeted faults into the CPU, the software's call graph can be escaped and the control-flow can be redirected to arbitrary…

Environmental noise (e.g.heat, ionized particles, etc.) causes transient faults in hardware, which lead to corruption of stored values. Mission-critical devices require such faults to be mitigated by fault-tolerance --- a combination of…

In this paper, we propose algorithms for handling non-integer strides in sampling-frequency-independent (SFI) convolutional and transposed convolutional layers. The SFI layers have been developed for handling various sampling frequencies…

To fully unlock the benefits of multiple-input multiple-output (MIMO) networks, downlink channel state information (CSI) is required at the base station (BS). In frequency division duplex (FDD) systems, the CSI is acquired through a…

Machine Unlearning (MU) is an increasingly important topic in machine learning safety, aiming at removing the contribution of a given data point from a training procedure. Federated Unlearning (FU) consists in extending MU to unlearn a…

Programs offer compactness and structure that makes them an attractive representation for visual data. We explore how code rewriting can be used to improve systems for inferring programs from visual data. We first propose Sparse…

The focus of this paper is on intrinsic methods to detect overfitting. By intrinsic methods, we mean methods that rely only on the model and the training data, as opposed to traditional methods (we call them extrinsic methods) that rely on…

Faults in high-performance systems are expected to be very large in the current exascale computing era. To compensate for a higher failure rate, the standard checkpoint/restart technique would need to create checkpoints at a much higher…

Continuous Integration and Continuous Deployment (CI/CD) pipeline automates software development to speed up and enhance the efficiency of engineering software. These workflows consist of various jobs, such as code validation and testing,…

Verifiable training has shown success in creating neural networks that are provably robust to a given amount of noise. However, despite only enforcing a single robustness criterion, its performance scales poorly with dataset complexity. On…

Fine-tuning is now the primary method for adapting large neural networks, but it also introduces new integrity risks. An untrusted party can insert backdoors, change safety behavior, or overwrite large parts of a model while claiming only…

In an offline reinforcement learning setting, the safe policy improvement (SPI) problem aims to improve the performance of a behavior policy according to which sample data has been generated. State-of-the-art approaches to SPI require a…

Federated learning (FL) has attracted much attention as a privacy-preserving distributed machine learning framework, where many clients collaboratively train a machine learning model by exchanging model updates with a parameter server…

Supervised fine-tuning (SFT) of large language models can be viewed as an off-policy learning problem, where expert demonstrations come from a fixed behavior policy while training aims to optimize a target policy. Importance sampling is the…

Control-flow leakage (CFL) attacks enable an attacker to expose control-flow decisions of a victim program via side-channel observations. Linearization (i.e., elimination) of secret-dependent control flow is the main countermeasure against…