Related papers: SpanKey: Dynamic Key Space Conditioning for Neural…

Direct-sequence spread spectrum (DSSS) has been recognized as an effective jamming resilient technique. However, the effectiveness of DSSS relies on the use of either pre-shared unique secret keys or a bank of public codes, which can be…

Recent work has shown that a model's input word embeddings can serve as effective control variables for steering its behavior toward outputs that satisfy desired properties. However, this has only been demonstrated for pretrained…

We propose a novel data-driven stochastic model predictive control framework for uncertain linear systems with noisy output measurements. Our approach leverages multi-step predictors to efficiently propagate uncertainty, ensuring chance…

Existing invasive (backdoor) fingerprints suffer from high-perplexity triggers that are easily filtered, fixed response patterns exposed by heuristic detectors, and spurious activations on benign inputs. We introduce \textsc{ForgetMark}, a…

Spiking neural networks (SNNs) have recently been attracting significant attention for their biological plausibility and energy efficiency, but semi-supervised learning (SSL) methods for SNN-based models remain underexplored compared to…

Insider threat is one of the most pressing threats in the field of information security as it leads to huge financial losses by the companies. Most of the proposed methods for detecting this threat require expensive and invasive equipment,…

Deep neural networks (DNNs) have achieved significant success in real-world applications. However, safeguarding their intellectual property (IP) remains extremely challenging. Existing DNN watermarking for IP protection often require…

In this paper, we propose privacy-preserving methods with a secret key for convolutional neural network (CNN)-based models in speech processing tasks. In environments where untrusted third parties, like cloud servers, provide CNN-based…

Existing RNN-based approaches for action recognition from depth sequences require either skeleton joints or hand-crafted depth features as inputs. An end-to-end manner, mapping from raw depth maps to action classes, is non-trivial to design…

We develop an approach to subspace system identification using multiple data records and present a simple rank-based test for the adequacy of these data for fitting the unique linear, noise-free, dynamic model of prescribed state-vector,…

Model stealing, i.e., unauthorized access and exfiltration of deep learning models, has become one of the major threats. Proprietary models may be protected by access controls and encryption. However, in reality, these measures can be…

Large-scale modern data often involves estimation and testing for high-dimensional unknown parameters. It is desirable to identify the sparse signals, ``the needles in the haystack'', with accuracy and false discovery control. However, the…

This article applies Machine Learning techniques to solve Intrusion Detection problems within computer networks. Due to complex and dynamic nature of computer networks and hacking techniques, detecting malicious activities remains a…

We present a novel approach to feature labeling using gradient descent in token-space. While existing methods typically use language models to generate hypotheses about feature meanings, our method directly optimizes label representations…

Brain-inspired spiking neural networks (SNNs) have recently drawn more and more attention due to their event-driven and energy-efficient characteristics. The integration of storage and computation paradigm on neuromorphic hardwares makes…

Backdoor attack has emerged as a novel and concerning threat to AI security. These attacks involve the training of Deep Neural Network (DNN) on datasets that contain hidden trigger patterns. Although the poisoned model behaves normally on…

Subsampling layers play a crucial role in deep nets by discarding a portion of an activation map to reduce its spatial dimensions. This encourages the deep net to learn higher-level representations. Contrary to this motivation, we…

Prior work on probing neural networks primarily relies on input-space analysis or parameter perturbation, both of which face fundamental limitations in accessing structural information encoded in intermediate representations. We introduce…

Evaluations of generative AI models often collapse nuanced behaviour into a single number computed for a single decoding configuration. Such point estimates obscure tail risks, demographic disparities, and the existence of multiple…

Spiking neural networks (SNNs) are the third generation of neural networks and can explore both rate and temporal coding for energy-efficient event-driven computation. However, the decision accuracy of existing SNN designs is contingent…