RAGCharacter localizes poisoned character spans in RAG evidence via prompt-conditioned counterfactual masking and achieves the best accuracy-over-attribution trade-off across tested attacks and models.
arXiv preprint arXiv:2410.14479 , year=
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
verdicts
UNVERDICTED 4roles
background 2polarities
background 2representative citing papers
RADAR defends RAG systems in dynamic settings by framing reliable context selection as a Max-Flow Min-Cut graph problem with Bayesian memory updates, claiming superior robustness, response quality, and low storage on a new dynamic dataset.
A memory-layer defense called Memory Sandbox stops persistent memory attacks on most LLM agents while other layer defenses fail.
A survey that taxonomizes threats to agentic AI, reviews benchmarks and evaluation methods, discusses technical and governance defenses, and identifies open challenges.
citing papers explorer
-
Needle-in-RAG: Prompt-Conditioned Character-Level Traceback of Poisoned Spans in Retrieved Evidence
RAGCharacter localizes poisoned character spans in RAG evidence via prompt-conditioned counterfactual masking and achieves the best accuracy-over-attribution trade-off across tested attacks and models.
-
RADAR: Defending RAG Dynamically against Retrieval Corruption
RADAR defends RAG systems in dynamic settings by framing reliable context selection as a Max-Flow Min-Cut graph problem with Bayesian memory updates, claiming superior robustness, response quality, and low storage on a new dynamic dataset.
-
Defense effectiveness across architectural layers: a mechanistic evaluation of persistent memory attacks on stateful LLM agents
A memory-layer defense called Memory Sandbox stops persistent memory attacks on most LLM agents while other layer defenses fail.
-
Agentic AI Security: Threats, Defenses, Evaluation, and Open Challenges
A survey that taxonomizes threats to agentic AI, reviews benchmarks and evaluation methods, discusses technical and governance defenses, and identifies open challenges.