💻 Category

cs

2787 papers

💻 computer science

Comparative Evaluation of Vision Transformer, Hybrid CNN–MLP, and Transfer-Learned ResNet-18 for CIFAR-10 Image Classification

This study evaluates Vision Transformer, hybrid CNN–MLP, and transfer-learned ResNet-18 models on CIFAR-10, finding that while the Vision Transformer learns meaningful representations, the transfer-learned ResNet-18 achieves the highest accuracy (88.7%) due to the advantages of convolutional inductive biases and large-scale pretraining in limited-data settings.

Laiba Ameer2026-08-11
💻 computer science

Remaining Useful Life Estimation of Lithium-Ion Batteries: A Controlled Benchmark of Physics-Informed Features and Mamba-Based Architectures on CALCE CS2

This paper presents a controlled benchmark on CALCE CS2 data showing that a standard GRU model outperforms advanced Mamba-based architectures in predicting lithium-ion battery remaining useful life, highlighting the critical importance of physics-informed features like capacity normalization while noting that current results reflect oracle-based evaluation rather than deployment-ready performance.

Dikshant Dikshant, Praveen Kumar Agarwal2026-08-11
💻 computer science

Decentralized AI-Powered Zero-Trust Identity and Access Management Using Blockchain and Deepfake-Resistant Multimodal Biometrics

This paper proposes a Decentralized AI-powered Zero-Trust IAM framework (DAZT-IAM) that integrates permissioned blockchain, self-sovereign identity, and deepfake-resistant multimodal biometrics with continuous risk-adaptive scoring to eliminate single points of failure and counter sophisticated impersonation attacks.

Anithalakshmi V¹, Raja P², N Sripriya, M Lavanya2026-08-11
💻 computer science

Swin-TCN-XAI: A Hybrid End-to-End Framework for Explainable Multi-Class Brain Tumor MRI Classification

This paper introduces Swin-TCN-XAI, a hybrid deep learning framework that integrates Swin Transformers and Temporal Convolutional Networks with multi-level explainability techniques to achieve state-of-the-art accuracy and clinical interpretability in multi-class brain tumor MRI classification.

Umme Sara, MSTMd. Mamu, MD IRFANUL KABIR HIRA, MD SOHAG HOSSAIN, Md. Kowsar Ahmed, Md. Mamun Ur Rashid2026-08-11
💻 computer science

Measuring How LLM Tool Descriptions, Cross-Tool Ambiguity, and Action Chains Compose into Excessive Agency Exploits

This paper introduces AGENTSPILL, an empirical audit demonstrating that large language models are highly susceptible to excessive agency exploits—achieving a 50.6% overall success rate—particularly through tool description injection and unconfirmed action chaining, which cause models to prioritize manipulated instructions over canonical tool definitions and autonomously execute destructive sequences.

Mohammadreza Rashidi2026-08-11
💻 computer science

Labelled-Metadata Channels and Declarative Payload Phrasing in Hidden Prompt Injection: A Cross-Format Measurement Study

This paper presents a cross-format measurement study demonstrating that indirect prompt injection vulnerabilities often stem from extraction pipelines failing to sanitize hidden payloads embedded in metadata, binary headers, and structured fields across diverse file formats, rather than from the LLMs' interpretation of the content itself.

Mohammadreza Rashidi2026-08-11
💻 computer science

The Claim-to-Action Gap: Measuring How Misinformation Turns False State into Tool Calls in Tool-Using LLM Agents

This paper introduces a novel framework for measuring the "claim-to-action" gap in tool-using LLM agents by demonstrating that false claims trigger harmful real-world actions in nearly 70% of trials, a vulnerability that is effectively neutralized (reducing the action rate to 0%) by implementing an OWASP-recommended verification step before execution.

Mohammadreza Rashidi2026-08-11