pith. sign in

Axiomatic attribution for deep networks,

2 Pith papers cite this work. Polarity classification is still indexing.

2 Pith papers citing it

citation-role summary

background 1

citation-polarity summary

fields

cs.CR 1 cs.IR 1

years

2026 1 2024 1

verdicts

UNVERDICTED 2

roles

background 1

polarities

background 1

representative citing papers

Trustworthiness in Retrieval-Augmented Generation Systems: A Survey

cs.IR · 2024-09-16 · unverdicted · novelty 7.0

Introduces Trust-RAG Compass framework and TRC Bench benchmark to assess RAG trustworthiness across factuality, robustness, fairness, transparency, accountability, and privacy, with evaluations showing performance gaps between LLMs.

Machine Learning-Based Detection of MCP Attacks

cs.CR · 2026-04-12 · unverdicted · novelty 6.0

Supervised ML models including SVC and BERT achieve 100% F1 on binary malicious/benign MCP tool detection and up to 90.56% on multiclass attack typing, outperforming rule-based baselines.

citing papers explorer

Showing 2 of 2 citing papers.

  • Trustworthiness in Retrieval-Augmented Generation Systems: A Survey cs.IR · 2024-09-16 · unverdicted · none · ref 130

    Introduces Trust-RAG Compass framework and TRC Bench benchmark to assess RAG trustworthiness across factuality, robustness, fairness, transparency, accountability, and privacy, with evaluations showing performance gaps between LLMs.

  • Machine Learning-Based Detection of MCP Attacks cs.CR · 2026-04-12 · unverdicted · none · ref 33

    Supervised ML models including SVC and BERT achieve 100% F1 on binary malicious/benign MCP tool detection and up to 90.56% on multiclass attack typing, outperforming rule-based baselines.