Related papers: PRIME: Plasticity-Robust Incremental Model for Enc…

Large Language Models (LLMs), constrained by their auto-regressive nature, suffer from slow decoding. Speculative decoding methods have emerged as a promising solution to accelerate LLM decoding, attracting attention from both systems and…

Recently we have witnessed the explosion of proposals that, inspired by Language Models like BERT, exploit Representation Learning models to create traffic representations. All of them promise astonishing performance in encrypted traffic…

The growing complexity of encrypted network traffic presents dual challenges for modern network management: accurate multiclass classification of known applications and reliable detection of unknown traffic patterns. Although deep learning…

When trained on large-scale object classification datasets, certain artificial neural network models begin to approximate core object recognition behaviors and neural response patterns in the primate brain. While recent machine learning…

Identifying threats in a network traffic flow which is encrypted is uniquely challenging. On one hand it is extremely difficult to simply decrypt the traffic due to modern encryption algorithms. On the other hand, passing such an encrypted…

We develop a continual learning method for pretrained models that \emph{requires no access to old-task data}, addressing a practical barrier in foundation model adaptation where pretraining distributions are often unavailable. Our key…

All the existing real world networks are evolving, hence, study of traffic dynamics in these enlarged networks is a challenging task. The critical issue is to optimize the network structure to improve network capacity and avoid traffic…

It is increasingly important to enable privacy-preserving inference for cloud services based on Transformers. Post-quantum cryptographic techniques, e.g., fully homomorphic encryption (FHE), and multi-party computation (MPC), are popular…

We introduce PRANCE, a Vision Transformer compression framework that jointly optimizes the activated channels and reduces tokens, based on the characteristics of inputs. Specifically, PRANCE~ leverages adaptive token optimization strategies…

Modern deep-learning systems are specialized to problem settings in which training occurs once and then never again, as opposed to continual-learning settings in which training occurs continually. If deep-learning systems are applied in a…

Network traffic analysis is fundamental for network management, troubleshooting, and security. Tasks such as traffic classification, anomaly detection, and novelty discovery are fundamental for extracting operational information from…

Understanding and quantifying node importance is a fundamental problem in network science and engineering, underpinning a wide range of applications such as influence maximization, social recommendation, and network dismantling. Prior…

Network traffic classification, a task to classify network traffic and identify its type, is the most fundamental step to improve network services and manage modern networks. Classical machine learning and deep learning method have…

Maximizing influences in complex networks is a practically important but computationally challenging task for social network analysis, due to its NP- hard nature. Most current approximation or heuristic methods either require tremendous…

Traffic classification, a technique for assigning network flows to predefined categories, has been widely deployed in enterprise and carrier networks. With the massive adoption of mobile devices, encryption is increasingly used in mobile…

Accurate inference of fine-grained traffic flow from coarse-grained one is an emerging yet crucial problem, which can help greatly reduce the number of the required traffic monitoring sensors for cost savings. In this work, we notice that…

While Mixture-of-Experts (MoE) scales capacity via conditional computation, Transformers lack a native primitive for knowledge lookup, forcing them to inefficiently simulate retrieval through computation. To address this, we introduce…

Open rule refer to the implication from premise atoms to hypothesis atoms, which captures various relations between instances in the real world. Injecting open rule knowledge into the machine helps to improve the performance of downstream…

In this paper, we consider the problem of fine-grained image retrieval in an incremental setting, when new categories are added over time. On the one hand, repeatedly training the representation on the extended dataset is time-consuming. On…

Adapting to concept drift is a challenging task in machine learning, which is usually tackled using incremental learning techniques that periodically re-fit a learning model leveraging newly available data. A primary limitation of these…