TrafficMoE proposes a Disentangle-Filter-Aggregate (DFA) framework using sparse Mixture-of-Experts to improve encrypted traffic classification by separating header and payload features and adaptively…

The paper proposes Mean MAE (MMAE), a novel self-supervised pre-training framework that uses flow mixing and teacher-student distillation to improve encrypted traffic classification by capturing multi…

The paper introduces an Integrated, cross-Architecture Reasoning (IAR) framework to provide a unified and robust method for interpreting the opaque reasoning processes within Large Language Models.

MambaNetBurst introduces a compact, tokenizer-free byte-level classifier using a Mamba-2 backbone to achieve strong network traffic classification without requiring pre-training or complex data prepro…

The paper proposes FreeUp, a frequency-decoupled framework that improves encrypted network anomaly detection by separately modeling and fusing low- and high-frequency components of traffic data.

This paper introduces an attribution-driven analysis of encoder-based Large Language Models (LLMs) for network intrusion detection, demonstrating that the models make decisions based on meaningful tra…

This paper demonstrates that reasoning-enabled Vision-Language-Action (VLA) models for autonomous driving are highly vulnerable to realistic input perturbations, significantly compromising both reason…

The paper introduces CAN-QA, a novel question-answering benchmark that reformulates CAN traffic analysis from a classification task to a reasoning task, demonstrating that current LLMs struggle with c…

GETA is a protocol-agnostic framework that analyzes encrypted network traffic using only metadata, achieving state-of-the-art performance across diverse tasks without needing large labeled datasets.

The paper proposes a training-free framework, Visual Representation-Guided Video-LLM Reasoning, to perform composed video retrieval by using visual examples and text instructions, achieving strong per…

The paper proposes SATA, a semantics-aware traffic augmentation framework, to significantly improve the generalization of website fingerprinting models by addressing variability in resource compositio…

The paper proposes CSMR, a cognitive scheduling framework that allows a language model to dynamically decide when to acquire task-relevant visual evidence, significantly improving multimodal reasoning…

The paper introduces X-Stream, a new benchmark for multi-stream video understanding, and finds that current state-of-the-art MLLMs perform poorly when required to process multiple concurrent video str…

The paper explains the 'table-chart gap' in scientific claim verification by showing that multimodal LLMs successfully encode information from charts but fail to route it to the final prediction layer…

The paper proposes SCOPE, a lightweight LLM framework that significantly improves the accuracy and efficiency of automated Air Traffic Control (ATC) readback monitoring, achieving high performance in…

The paper identifies a universal, statistically predictable distribution (Mandelbrot) governing LLM outputs, enabling a highly efficient, model-agnostic scoring primitive for provenance and quality as…

The paper proposes an embarrassingly simple detector that monitors model extraction attacks by testing whether the aggregate distribution of incoming LLM queries deviates from the historical distribut…

The paper proposes a structured prompt engineering framework to enhance the integrity and reliability of Chain-of-Thought (CoT) reasoning in LLMs, demonstrating significant improvements in security-se…

This paper introduces an active traffic analysis method (NATA) and a deep learning framework (BM-Net) to demonstrate that bandwidth perturbations can be used by an adversary to correlate and de-anonym…

This survey provides a comprehensive taxonomy and vulnerability-centric analysis of adversarial attacks targeting Multimodal Large Language Models (MLLMs), offering an explanatory framework for enhanc…