Adversarial Threat Vectors and Risk Mitigation for Retrieval-Augmented Generation Systems
Retrieval-Augmented Generation (RAG) systems, which integrate Large Language Models (LLMs) with external knowledge sources, are vulnerable to a range of adversarial attack vectors. This paper examines the importance of RAG systems through recent industry adoption trends and identifies the prominent attack vectors for RAG: prompt injection, data poisoning, and adversarial query manipulation. We analyze these threats under risk management lens, and propose robust prioritized control list that includes risk-mitigating actions like input validation, adversarial training, and real-time monitoring.
Code (0)
등록된 구현이 없습니다.
Tasks
Adversarial AttackData PoisoningManagementRAGRetrievalRetrieval-augmented GenerationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Eroding Trust In Aerial Imagery: Comprehensive Analysis and Evaluation Of Adversarial Attacks In Geospatial Systems
In critical operations where aerial imagery plays an essential role, the integrity and trustworthiness of data are paramount. The emergence of adversarial attacks, particularly those that exploit control over labels or e…
A Formal Framework for Assessing and Mitigating Emergent Security Risks in Generative AI Models: Bridging Theory and Dynamic Risk Mitigation
As generative AI systems, including large language models (LLMs) and diffusion models, advance rapidly, their growing adoption has led to new and complex security risks often overlooked in traditional AI risk assessment …
Anomaly DetectionRed TeamingAutonomous AI-based Cybersecurity Framework for Critical Infrastructure: Real-Time Threat Mitigation
Critical infrastructure systems, including energy grids, healthcare facilities, transportation networks, and water distribution systems, are pivotal to societal stability and economic resilience. However, the increasing …
Vulnerability DetectionGoal-Driven Risk Assessment for LLM-Powered Systems: A Healthcare Case Study
While incorporating LLMs into systems offers significant benefits in critical application areas such as healthcare, new security challenges emerge due to the potential cyber kill chain cycles that combine adversarial mod…
A Zero Trust Framework for Realization and Defense Against Generative AI Attacks in Power Grid
Understanding the potential of generative AI (GenAI)-based attacks on the power grid is a fundamental challenge that must be addressed in order to protect the power grid by realizing and validating risk in new attack vec…
Ensemble Learning