A Self-Explainable Deep Architecture for Security Applications

arXiv:2608.05552 · cs.CR · Submitted 2026-08-06 · Read on arXiv

Ananth Shreekumar, Jyun-Jhu Syu, Muslum Ozgur Ozmen, Dongyan Xu, Z. Berkay Celik

cs.CR

Submitted: 2026-08-06

Code: https://github.com/ashreeku/XSec

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Fidelity — 41× in this paper · explained in 2 episodes
• Sparsity — 28× in this paper · explained in 5 episodes
• Interpretability — 12× in this paper · explained in 15 episodes
• Accuracy — 11× in this paper · explained in 1 episode
• Augmentation — 10× in this paper · explained in 2 episodes
• Transformer — 9× in this paper · explained in 2 episodes
• Generator — 7× in this paper · explained in 2 episodes
• Embeddings — 6× in this paper · explained in 2 episodes
• Ablation — 5× in this paper · explained in 1 episode
• Explainability — 5× in this paper · explained in 4 episodes
• Robustness — 5× in this paper · explained in 6 episodes
• Saliency Maps — 5× in this paper
• Adam — 4× in this paper · explained in 3 episodes
• Cosine Similarity — 4× in this paper · explained in 3 episodes
• Faithfulness — 4× in this paper · explained in 2 episodes
• Feature Extraction — 4× in this paper · explained in 3 episodes
• Hyperparameters — 4× in this paper · explained in 2 episodes
• Feature Importance — 3× in this paper · explained in 2 episodes
• Feature Selection — 3× in this paper · explained in 4 episodes
• AUC — 2× in this paper · explained in 2 episodes
• Fine-Tuning — 2× in this paper · explained in 5 episodes
• Mean Around Zero — 2× in this paper
• Transformers — 2× in this paper · explained in 2 episodes
• Ablation Study — 1× in this paper · explained in 3 episodes
• Adversarial Examples — 1× in this paper · explained in 2 episodes
• Attack Success Rate (ASR) — 1× in this paper · explained in 3 episodes
• Concept Drift — 1× in this paper · explained in 6 episodes
• Dimensionality Reduction — 1× in this paper · explained in 2 episodes
• EMMA — 1× in this paper · explained in 2 episodes
• Explainable AI (XAI) — 1× in this paper · explained in 7 episodes
• Integrated Gradients — 1× in this paper
• Integrated Gradients (IG) — 1× in this paper · explained in 2 episodes
• Localization — 1× in this paper · explained in 2 episodes
• Model Interpretability — 1× in this paper · explained in 2 episodes
• Model-Agnostic — 1× in this paper · explained in 2 episodes
• Regularization — 1× in this paper · explained in 3 episodes
• Reinforcement Learning — 1× in this paper · explained in 4 episodes
• Surrogate Model — 1× in this paper · explained in 3 episodes
• Surrogate Models — 1× in this paper · explained in 3 episodes
• Transformer Architecture — 1× in this paper · explained in 4 episodes

Sources

• Explaining and Harnessing Adversarial Examples
• SmoothGrad: removing noise by adding noise
• Linearly-Interpretable Concept Embedding Models for Text Analysis

Related papers

• SoK: AI-Augmented Binary Reversing
• Relaxed Sender Anonymity for CBDC Interbank Settlement: A Zero-Knowledge Approach on Permissioned EVM
• Calibration-Family Overfit: Why Trusted Sabotage Monitors Don't Transfer Across Lineages
• Estimating the Social Cost of Corporate Data Breaches
• Efficient Fuzzy PSI under One-Sided Assumptions
• Sealing the Audit-Runtime Gap for LLM Skills