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.
and Teglia, Y
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
roles
background 2polarities
background 2representative citing papers
CAREATTACK adapts closed-form parameter editing with graph-based conflict resolution and lightweight anchor repair to promote malicious passages in RAG retrieval while limiting side effects on non-target queries.
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 survey that maps safety risks in personalized LLMs, introduces a unified taxonomy, and highlights three structural inadequacies in existing research on user-invariant safety, isolated techniques, and short-term evaluations.
A survey that taxonomizes threats to agentic AI, reviews benchmarks and evaluation methods, discusses technical and governance defenses, and identifies open challenges.
A survey of architectures, threats, defenses, and future directions for security and privacy in RAG systems.
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.
-
Conflict-Aware Retriever Editing for Knowledge Injection Attacks on LLM-Based RAG Systems
CAREATTACK adapts closed-form parameter editing with graph-based conflict resolution and lightweight anchor repair to promote malicious passages in RAG retrieval while limiting side effects on non-target queries.
-
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.
-
Personalization Meets Safety:Mechanisms,Risks,and Mitigations in Personalized LLMs
A survey that maps safety risks in personalized LLMs, introduces a unified taxonomy, and highlights three structural inadequacies in existing research on user-invariant safety, isolated techniques, and short-term evaluations.
-
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.
-
Security and Privacy in Retrieval-Augmented Generation: Architectures, Threats, Defenses, and Future Directions for Building Trustworthy Systems
A survey of architectures, threats, defenses, and future directions for security and privacy in RAG systems.
- Injection-Execution Dissociation: A Mechanistic Evaluation of Persistent Memory Attacks and Defenses in Stateful LLM Agents