BGA: A noise-immune neural distillation framework for malicious signature extraction in high-entropy encrypted flows

• URL: http://arxiv.org/abs/2608.14126v1
• Date: Fri, 14 Aug 2026 09:33:16 GMT
• Title: BGA: A noise-immune neural distillation framework for malicious signature extraction in high-entropy encrypted flows
• Abstract summary: We propose BGA, a noise-immune neural distillation framework for encrypted threat intelligence.<n>The architecture integrates Bidirectional Long-Term Memory (BiLSTM) for temporal dependency extraction and an Adaptive Gated Multi-Head Attention mechanism.<n>Extensive evaluations on CIC-IDS-2018 and Edge-IIoT benchmarks demonstrate a performance ceiling exceeding 9 latency across all key metrics.
• Score: 12.604432348059133
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: To mitigate attention dilution in high-entropy TLS 1.3 flows, we propose BGA, a noise-immune neural distillation framework for encrypted threat intelligence.The methodology first employs Analysis of Variance (ANOVA) to decouple high-discriminatory control-plane features - specifically industrial setpoints - from stochastic cryptographic noise. To resolve the extreme class imbalance within a corpus of 86,878 flow records, a Wasserstein GAN with Gradient Penalty (WGAN-GP) module, enforcing the 1-Lipschitz constraint, is integrated to synthesize high-fidelity minority samples, elevating the detection recall of rare Malicious State Command Injections(MSCI) attacks by 43.2%. At its core, the BGA architecture integrates Bidirectional Long Short-Term Memory (BiLSTM) for temporal dependency extraction and an Adaptive Gated Multi-Head Attention mechanism. This gated unit functions as a neural filter to dynamically suppress encryption artifacts while amplifying malicious signatures. Extensive evaluations on CIC-IDS-2018 and Edge-IIoT benchmarks demonstrate a performance ceiling exceeding 95.2% across all key metrics. Furthermore, noise-injection stress tests confirm BGAs superior structural resilience with a 8.57% performance margin over vanilla Transformers, while its ultra-low inference latency of 0.2820 ms (estimated 1.6920 ms via theoretical scaling for ARM) indicates a high potential for real-time feasibility on heterogeneous industrial edge gateways, providing a promising architectural baseline for future hardware implementation.

Related papers

• RAGDiffusion++: From Macro-Retrieval to Micro-Fidelity Alignment for Garment Generation [41.42598259381642]
  Reinforcement Learning can reshape the sampling distribution of flow models.<n>Garment-RM trained on 500K images via fine-grained contrastive learning, achieving 84.67% human preference accuracy.<n>Our strategy integrates a dynamic discriminator into the RL sampling trajectory to penalize artifacts while enriching authentic high-frequency details.
  arXiv  Detail & Related papers  (2026-08-29T14:06:09Z)
• A Deployment-Oriented and Resource-Efficient Neuro-Symbolic Framework for Explainable DDoS Detection in Operational Technology Networks [1.202468381202799]
  This paper presents a neuro-symbolic framework specifically designed for robust DDoS detection in resource-constrained environments.<n>The framework fuses a gated recurrent unit (GRU) neural network with a shallow decision tree as a symbolic component.<n>The hybrid model is evaluated on three real-world benchmark DDoS datasets.
  arXiv  Detail & Related papers  (2026-08-17T16:18:15Z)
• Screening of Biosecurity Features in Metagenomic Data with Evo 2 Probes [35.18016233072556]
  Genomic foundation models such as Evo 2 learn rich sequence representations, but their value for biosecurity screening is largely unexplored.<n>We ask how much biosecurity-relevant signal is linearly accessible in these representations by training minimal linear and attention probes on frozen Evo 2 layer-26 activations.<n>Across held-out metagenomic test sets, the probes detect antimicrobial resistance with strong discrimination.
  arXiv  Detail & Related papers  (2026-07-15T17:38:02Z)
• Cascaded Multi-Granularity Pruning for On-Device LLM Inference in Industrial IoT [4.775543545907101]
  This article presents a cascaded multi-granularity pruning framework that removes layers, attention heads, and feed-forward channels in coarse-to-fine order.<n>An information-theoretic analysis motivates this ordering, and the Structural Independence Assumption (SIA) is formalized as a checkable condition.<n> Deployed on an industrial slewing bearing fault diagnosis platform with NVIDIA DGX Spark, compressed models reduce inference latency by up to 67.2% and peak memory by 62.5%.
  arXiv  Detail & Related papers  (2026-06-25T10:44:48Z)
• Federated Temporal Attention Intelligence for Cyber-Resilient IoMT: Lightweight Digital Twins and PPO-Driven Honeypot Deception [0.6095710009266794]
  The rapid proliferation of Internet of Medical Things (IoMT) devices introduces critical cybersecurity vulnerabilities in healthcare environments.<n>This paper presents the Lightweight Digital Twin and Federated Reinforcement Learning framework, a privacy-preserving defense architecture integrating four complementary mechanisms.
  arXiv  Detail & Related papers  (2026-06-19T13:40:57Z)
• GenAI for Energy-Efficient and Interference-Aware Compressed Sensing of GNSS Signals on a Google Edge TPU [37.74014735747033]
  This paper introduces a novel method for compressing and classifying jamming threats using generative artificial intelligence (GenAI)<n>Our proposed approach efficiently compresses data streams directly at the hardware receiver while simultaneously classifying jamming and spoofing attacks in real time.<n>The hardware-centric GenAI approach also substantially reduces jammer signal transmission costs, offering a practical solution for interference mitigation.
  arXiv  Detail & Related papers  (2026-05-14T13:43:55Z)
• FEMBA on the Edge: Physiologically-Aware Pre-Training, Quantization, and Deployment of a Bidirectional Mamba EEG Foundation Model on an Ultra-low Power Microcontroller [13.961569964076451]
  We present FEMBA, a bidirectional Mamba architecture pre-trained on over 21,000 hours of EEG.<n>We introduce a novel Physiologically-Aware pre-training objective, consisting of a reconstruction with low-pass filtering.<n>We employ Quantization-Aware Training (QAT) to compress the model to 2-bit weights.
  arXiv  Detail & Related papers  (2026-03-18T13:23:13Z)
• Beyond Reward Suppression: Reshaping Steganographic Communication Protocols in MARL via Dynamic Representational Circuit Breaking [0.0]
  steganographic collusion, where agents develop private protocols to evade monitoring, presents a critical AI safety threat.<n>Existing defenses, limited to behavioral or reward layers, fail to detect coordination in latent communication channels.<n>We introduce the Dynamic Representational Circuit Breaker (DRCB), an architectural defense operating at the optimization substrate.
  arXiv  Detail & Related papers  (2026-03-07T04:14:38Z)
• MI$^2$DAS: A Multi-Layer Intrusion Detection Framework with Incremental Learning for Securing Industrial IoT Networks [47.386868423451595]
  MI$2$DAS is a multi-layer intrusion detection framework that integrates anomaly-based hierarchical traffic pooling and open-set recognition.<n>Experiments conducted on the Edge-IIoTset dataset demonstrate strong performance across all layers.<n>These results showcase MI$2$DAS as an effective, scalable and adaptive framework for enhancing IIoT security.
  arXiv  Detail & Related papers  (2026-02-27T09:37:05Z)
• BadCLIP++: Stealthy and Persistent Backdoors in Multimodal Contrastive Learning [73.46118996284888]
  Research on backdoor attacks against multimodal contrastive learning models faces two key challenges: stealthiness and persistence.<n>We propose BadCLIP++, a unified framework that tackles both challenges.<n>For stealthiness, we introduce a semantic-fusion QR micro-trigger that embeds imperceptible patterns near task-relevant regions.<n>For persistence, we stabilize trigger embeddings via radius shrinkage and centroid alignment.
  arXiv  Detail & Related papers  (2026-02-19T08:31:16Z)
• Halt the Hallucination: Decoupling Signal and Semantic OOD Detection Based on Cascaded Early Rejection [7.227431306238601]
  We propose the Cascaded Early Rejection (CER) framework, which realizes hierarchical filtering for anomaly detection via a coarse-to-fine logic.<n> Experimental results demonstrate that CER not only reduces computational overhead by 32% but also achieves a significant performance leap on the CIFAR-100 benchmark.
  arXiv  Detail & Related papers  (2026-02-06T02:55:35Z)
• Provable Defense Framework for LLM Jailbreaks via Noise-Augumented Alignment [37.06683377953812]
  Large Language Models (LLMs) remain vulnerable to adaptive jailbreaks that easily bypass empirical defenses like GCG.<n>We propose a framework for certifiable robustness that shifts safety guarantees from single-pass inference to the statistical stability of an ensemble.
  arXiv  Detail & Related papers  (2026-02-02T03:26:45Z)
• SKANet: A Cognitive Dual-Stream Framework with Adaptive Modality Fusion for Robust Compound GNSS Interference Classification [47.20483076887704]
  Global Navigation Satellite Systems (GNSS) face growing threats from sophisticated jamming interference.<n>We propose a cognitive deep learning framework built upon a dual-stream architecture that integrates Time-Frequency Images (TFIs) and Power Spectral Density (PSD)<n>We show that SKANet achieves an overall accuracy of 96.99%, exhibiting superior robustness for compound jamming classification.
  arXiv  Detail & Related papers  (2026-01-19T07:42:45Z)
• DT-DDNN: A Physical Layer Security Attack Detector in 5G RF Domain for CAVs [10.215216950059874]
  jamming attacks pose substantial risks to the 5G network.<n>This work presents a novel deep learning-based technique for detecting jammers in CAV networks.<n>Results show that the proposed method achieves 96.4% detection rate in extra low jamming power.
  arXiv  Detail & Related papers  (2024-03-05T04:29:31Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.