DiscourseFlip is a graph-guided attack allocating limited poisoning budget to induce targeted opinion shifts over semantic query networks in black-box RAG.
Hijack- rag: Hijacking attacks against retrieval-augmented large language models.arXiv preprint arXiv:2410.22832, 2024
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 5roles
background 1polarities
support 1representative citing papers
A new 7x4 taxonomy organizes agentic AI security threats by architectural layer and persistence timescale, revealing under-explored upper layers and missing defenses after surveying 116 papers.
A single query-specific poisoned document, built by extracting and iteratively refining an adversarial chain-of-thought, can substantially degrade reasoning accuracy in retrieval-augmented LLM systems.
AuthChain poisons a single document to achieve high-success attacks on RAG systems for multi-hop queries across six LLMs while evading defenses.
Introduces ANIS as an endogenous, six-layer immune architecture for AI agents with taxonomy of viruses/vaccines and a meta-cognitive Harness Triad for continual adaptation.
citing papers explorer
-
DiscourseFlip: An Oblique Discourse-Level Opinion Manipulation Attack against Black-box Retrieval-Augmented Generation
DiscourseFlip is a graph-guided attack allocating limited poisoning budget to induce targeted opinion shifts over semantic query networks in black-box RAG.
-
A Systematic Survey of Security Threats and Defenses in LLM-Based AI Agents: A Layered Attack Surface Framework
A new 7x4 taxonomy organizes agentic AI security threats by architectural layer and persistence timescale, revealing under-explored upper layers and missing defenses after surveying 116 papers.
-
AdversarialCoT: Single-Document Retrieval Poisoning for LLM Reasoning
A single query-specific poisoned document, built by extracting and iteratively refining an adversarial chain-of-thought, can substantially degrade reasoning accuracy in retrieval-augmented LLM systems.
-
One Shot Dominance: Knowledge Poisoning Attack on Retrieval-Augmented Generation Systems
AuthChain poisons a single document to achieve high-success attacks on RAG systems for multi-hop queries across six LLMs while evading defenses.
-
Agent-Native Immune System: Architecture, Taxonomy, and Engineering
Introduces ANIS as an endogenous, six-layer immune architecture for AI agents with taxonomy of viruses/vaccines and a meta-cognitive Harness Triad for continual adaptation.