- Rating
- 3(+1)
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
The paper proposes a new attacks against Agentic RAG. The attack makes the agent to believe it needs to retrieve more information from the RAG, in the end resulting in a loop. The authors show how to construct the series of documents that will poison the corpus, based on the queries the attacks wants to induce on the agent. They demonstrate the attack on several models and they also compare it with two simple defenses.
Critical strengths
The problem setting is realistic from the point of view of attacker capabilities and knowledge. They demonstrate that creating the documents to induce the loop is indeed necessary, vs just having a random sequence of documents.
Critical weaknesses
There are system level defenses that can mitigate the attack or raise the bar for the attacker that are not explored such us preventing RAG poisoning in the first place by using security policies that control the documents accepted in the RAG. For web based documents indeed that might be a bit more difficult to control but it will also be more difficult for the attacker.
I did not see an evaluation of the overhead needed to generate the poisoned documents and the effectiveness of the attack based on the length of the loop.
Questions for authors
How long does it take to generate the poisoned documents based on the length of the loop?
Does the length of the loop matter for attack effectiveness?
3 comments
Response to W2, Q1 adn Q2
[W2, Q1] What is the overhead of generating poisoned documents, and how does it vary with cycle length?
Poisoned-document generation takes minutes per task and has low estimated monetary costs, both increasing with cycle length. We measure offline attack-construction costs on the same 100 SQuAD questions with cycle lengths (k ∈ {3,5,7}). We report mean wall-clock time and total auxiliary-model tokens per task. API-equivalent costs are estimated using Qwen2.5-Coder-7B-Instruct at $0.05 per million input/output tokens.
Table.R2: Offline attack-construction costs across cycle lengths on 100 SQuAD tasks.
| Cycle length k | Mean preparation time (s) | Auxiliary-model tokens per task | Estimated cost per task (USD) |
|---|---|---|---|
| 3 | 117.14 | 24524.2 | $0.00123 |
| 5 | 157.50 | 42807.4 | $0.00214 |
| 7 | 231.60 | 55796.6 | $0.00279 |
These minute-scale preparation times are practical for offline attacks, while the estimated monetary costs are negligible, supporting the practical feasibility of attack construction.
[W2, Q2] Does the length of the loop matter for attack effectiveness?
Cycle length affects attack effectiveness, but longer cycles do not consistently yield greater resource amplification. We compare cycle lengths k ∈ {3,5,7} on the same 200 SQuAD questions, keeping all other settings fixed.
Table.R3: Resource amplification by cycle length on the same 200 SQuAD tasks.
| Victim model | Cycle length k | TCR | ΔSTEPS | ΔCAP HITS (pp) |
|---|---|---|---|---|
| Qwen3.5-4B | 3 | 32.39 | 9.14 | 8 |
| 5 | 35.44 | 10.20 | 10 | |
| 7 | 58.54 | 14.03 | 18 | |
| Qwen3.5-9B | 3 | 69.10 | 5.31 | 27 |
| 5 | 97.42 | 9.19 | 29 | |
| 7 | 88.79 | 7.60 | 14 |
Cycle length introduces a trade-off between resource consumption and attack success. Longer cycles can incur greater retrieval overhead per completed cycle, but require more successful query transitions, increasing the risk of breaking the cycle. Consequently, longer cycles do not necessarily lead to greater overall resource amplification.
I have read the answer and will raise my score.
Response to W1
[W1] Could broader system-level defenses, including document admission policies, mitigate the attack or raise the attacker’s barrier?
System-level defenses can raise the attacker's barrier but do not necessarily eliminate corpus-poisoning risks. Our threat model assumes that the attacker can insert a small number of poisoned documents into the retrieval corpus, for example through a contributor account in a shared enterprise knowledge base. This setting is consistent with PoisonedRAG [1], which explicitly considers insider insertion into enterprise knowledge bases and poisoning through web sources. CorruptRAG [2] further demonstrates that effective RAG poisoning can require only a single poisoned text per target query. These studies support limited corpus poisoning as a valid threat model.
We have already evaluated two distinct defenses, Perplexity Filtering and Keyword-Density Filtering, to filter and control the documents actually read by Agentic RAG, and verified that CyclicRA remains effective under these defenses (Section 5.2).
To further strengthen our evaluation, we additionally consider a more sophisticated, behavior-aware system-level defense, LoopGuard, which monitors agent execution to detect repetitive and cyclic behavior. We evaluate LoopGuard on 200 SQuAD attack trajectories across four models. The results are presented below:
Table.R1: LoopGuard warning and interception rates on 200 SQuAD attack trajectories (%).
CyclicRA achieves the lowest warning rate across all evaluated models and the lowest interception rate on two, suggesting that its nonconsecutive query revisits are harder for LoopGuard to detect under the current configuration.
[1] Zou, W., et al. (2025). PoisonedRAG: Knowledge Corruption Attacks to Retrieval-Augmented Generation of Large Language Models. Proceedings of the 34th USENIX Security Symposium, 3827–3844.
[2] Zhang, B., et al. (2026). Practical Poisoning Attacks against Retrieval-Augmented Generation. arXiv preprint arXiv:2504.03957.