# Joint-GCG: Unified Gradient-Based Poisoning Attacks on Retrieval-Augmented Generation Systems

arXiv: https://arxiv.org/abs/2506.06151 · HTML: https://mlsanity.com/paper/2506.06151/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- Placed in Privacy and security of RAG, one of 15 directions in Retrieval-augmented generation.
- Builds on 30 of its 46 references that are in the map.
- First posted on arXiv 6 Jun 2025.

## Placed in

- Retrieval-augmented generation / [Privacy and security of RAG](https://mlsanity.com/rag/privacy-and-security-of-rag/)

## Builds on (most cited first, 30 of 30)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [Universal and Transferable Adversarial Attacks on Aligned Language Models](https://mlsanity.com/paper/2307.15043/) (2023)
- [Retrieval-Augmented Generation for Large Language Models: A Survey](https://mlsanity.com/paper/2312.10997/) (2023)
- [Qwen2 Technical Report](https://mlsanity.com/paper/2407.10671/) (2024)
- [MS MARCO: A Human Generated MAchine Reading COmprehension Dataset](https://mlsanity.com/paper/1611.09268/) (2016)
- [Unsupervised Dense Information Retrieval with Contrastive Learning](https://mlsanity.com/paper/2112.09118/) (2021)
- [When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memories](https://mlsanity.com/paper/2212.10511/) (2022)
- [Ethical and social risks of harm from Language Models](https://mlsanity.com/paper/2112.04359/) (2021)
- [In-Context Retrieval-Augmented Language Models](https://mlsanity.com/paper/2302.00083/) (2023)
- [C-Pack: Packed Resources For General Chinese Embeddings](https://mlsanity.com/paper/2309.07597/) (2023)
- [BERT-ATTACK: Adversarial Attack Against BERT Using BERT](https://mlsanity.com/paper/2004.09984/) (2020)
- [SmoothLLM: Defending Large Language Models Against Jailbreaking Attacks](https://mlsanity.com/paper/2310.03684/) (2023)
- [A Survey on RAG Meeting LLMs: Towards Retrieval-Augmented Large Language Models](https://mlsanity.com/paper/2405.06211/) (2024)
- [Detecting Language Model Attacks with Perplexity](https://mlsanity.com/paper/2308.14132/) (2023)
- [TextBugger: Generating Adversarial Text Against Real-world Applications](https://mlsanity.com/paper/1812.05271/) (2018)
- [Adversarial Attacks and Defences: A Survey](https://mlsanity.com/paper/1810.00069/) (2018)
- [Dataset Security for Machine Learning: Data Poisoning, Backdoor Attacks, and Defenses](https://mlsanity.com/paper/2012.10544/) (2020)
- [DocPrompting: Generating Code by Retrieving the Docs](https://mlsanity.com/paper/2207.05987/) (2022)
- [Improving the Domain Adaptation of Retrieval Augmented Generation (RAG) Models for Open Domain Question Answering](https://mlsanity.com/paper/2210.02627/) (2022)
- [Improved Techniques for Optimization-Based Jailbreaking on Large Language Models](https://mlsanity.com/paper/2405.21018/) (2024)
- [BadRAG: Identifying Vulnerabilities in Retrieval Augmented Generation of Large Language Models](https://mlsanity.com/paper/2406.00083/) (2024)
- [Manipulating SGD with Data Ordering Attacks](https://mlsanity.com/paper/2104.09667/) (2021)
- [TrojanRAG: Retrieval-Augmented Generation Can Be Backdoor Driver in Large Language Models](https://mlsanity.com/paper/2405.13401/) (2024)
- ["Glue pizza and eat rocks" -- Exploiting Vulnerabilities in Retrieval-Augmented Generative Models](https://mlsanity.com/paper/2406.19417/) (2024)
- [Data Poisoning Attacks on Stochastic Bandits](https://mlsanity.com/paper/1905.06494/) (2019)
- [Phantom: General Backdoor Attacks on Retrieval Augmented Language Generation](https://mlsanity.com/paper/2405.20485/) (2024)
- [From Allies to Adversaries: Manipulating LLM Tool-Calling through Adversarial Injection](https://mlsanity.com/paper/2412.10198/) (2024)
- [A Survey on Adversarial Information Retrieval on the Web](https://mlsanity.com/paper/1911.11060/) (2019)

## Built on by (most cited first, 16 of 16)

- [RIPRAG: Hack a Black-box Retrieval-Augmented Generation Question-Answering System with Reinforcement Learning](https://mlsanity.com/paper/2510.10008/) (2025)
- [Confundo: Learning to Generate Robust Poison for Practical RAG Systems](https://mlsanity.com/paper/2602.06616/) (2026)
- [ProGRank: Probe-Gradient Reranking to Defend Dense-Retriever RAG from Corpus Poisoning](https://mlsanity.com/paper/2603.22934/) (2026)
- [Securing Retrieval-Augmented Generation: A Taxonomy of Attacks, Defenses, and Future Directions](https://mlsanity.com/paper/2604.08304/) (2026)
- [RAGuard: A Layered Defense Framework for Retrieval-Augmented Generation Systems Against Data Poisoning](https://mlsanity.com/paper/2607.26339/) (2026)
- [SilentRetrieval: Hijacking Retrieval-Augmented Generation via Semantically-Preserving Adversarial Data Poisoning](https://mlsanity.com/paper/2605.28074/) (2026)
- [Retrieved But Not Reliable: A Survey on Attacks, and Defenses in Retrieval-Augmented Generation](https://mlsanity.com/paper/2608.24977/) (2026)
- [ImageAuditor: Membership Inference Attack against Image-based Retrieval-Augmented Generation](https://mlsanity.com/paper/2606.03354/) (2026)
- [When Poison Fails After Retrieval: Revisiting Corpus Poisoning under Chunking and Reranking Pipelines](https://mlsanity.com/paper/2606.11265/) (2026)
- [Large Language Models in Misinformation Ecosystems: Misuse, Defense, and Vulnerability](https://mlsanity.com/paper/2607.10402/) (2026)
- [TriShieldRAG: 3 Rings, One Blind Spot in Layered Defenses for Retrieval-Augmented Generation](https://mlsanity.com/paper/2607.23838/) (2026)
- [DenialRAG: Single-Document RAG Poisoning via Embedded Parametric Denial](https://mlsanity.com/paper/2608.02678/) (2026)
- [Micro-Collaborative Poisoning: A Distributed Attack on RAG Systems](https://mlsanity.com/paper/2609.21573/) (2026)
- [When the Agent Becomes the Kernel: A Systematization of Security on the Path to AI-Native Operating Systems](https://mlsanity.com/paper/2609.23700/) (2026)
- [RAG-NAROK: Retrieval-Aware Knowledge Corpus Poisoning in RAG with Source-specific Refutation](https://mlsanity.com/paper/2609.25469/) (2026)
- [Divide and Doubt: Diverse Distributed Poisoning for Retrieval-Augmented Generation](https://mlsanity.com/paper/2609.27090/) (2026)

## Abstract (arXiv)

Retrieval-Augmented Generation (RAG) systems enhance Large Language Models (LLMs) by retrieving relevant documents from external corpora before generating responses. This approach significantly expands LLM capabilities by leveraging vast, up-to-date external knowledge. However, this reliance on external knowledge makes RAG systems vulnerable to corpus poisoning attacks that manipulate generated outputs via poisoned document injection. Existing poisoning attack strategies typically treat the retrieval and generation stages as disjointed, limiting their effectiveness. We propose Joint-GCG, the first framework to unify gradient-based attacks across both retriever and generator models through three innovations: (1) Cross-Vocabulary Projection for aligning embedding spaces, (2) Gradient Tokenization Alignment for synchronizing token-level gradient signals, and (3) Adaptive Weighted Fusion for dynamically balancing attacking objectives. Evaluations demonstrate that Joint-GCG achieves at most 25% and an average of 5% higher attack success rate than previous methods across multiple retrievers and generators. While optimized under a white-box assumption, the generated poisons show unprecedented transferability to unseen models. Joint-GCG's innovative unification of gradient-based attacks across retrieval and generation stages fundamentally reshapes our understanding of vulnerabilities within RAG systems. Our code is available at https://github.com/NicerWang/Joint-GCG.