- Rating
- 2
- Confidence
- 3
- Informativeness
- 1
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper studies a new backdoor attack scenario, where malicious users can leverage a trigger to elicit a verbose response from LLMs, which can potentially increase inference costs. Experiments across 4 LLMs and two summarization datasets demonstrate substantial response inflation while largely preserving output fidelity. In addition, the authors propose a defense method to combat this attack.
Critical strengths
-
The authors introduce a data-poisoning attack that increases response length by approximately 1.6–7.3×, potentially raising inference costs without substantially compromising response quality.
-
The authors propose a defense method that can recover their trigger phrases and mitigate the backdoor effects through lightweight fine-tuning. Experiments show substantially fewer false positives than a length-only detection baseline, improved trigger recovery, and post-mitigation inflation rates close to the benign model.
Critical weaknesses
- The proposed attack primarily changes the target behavior of conventional instruction-tuning data poisoning from incorrect or malicious outputs to excessively long responses. Likewise, the defense largely adapts the existing Class Subspace Orthogonalization (CSO) framework by replacing its classification-oriented objective with a response-length objective. Moreover, the generalization of trigger synonyms/pharaphse has been observed and studied in [1].
- The evaluation is restricted to two summarization datasets, where the achievable response inflation appears strongly influenced by the relative lengths of short and long reference summaries. More fundamentally, the paper does not investigate whether the attack remains effective under shifts in response-length distributions between poisoning and deployment. For instance, if poisoned training examples contain relatively short target responses while test-time tasks naturally require much longer outputs, it is unclear whether the learned backdoor would still induce meaningful response inflation or additional inference costs. This raises concerns about whether the reported effectiveness reflects a generalizable backdoor mechanism or is largely driven by dataset-specific length characteristics. It remains unclear whether the proposed attack generalizes beyond summarization to broader instruction-following tasks with different response-length characteristics. Nevertheless, the authors frame their findings as a general vulnerability of LLMs throughout the title, abstract, and introduction. Such broad claims are not supported by the narrow experimental scope, limited to two summarization datasets.
- The combination of a relatively straightforward attack mechanism and an effective adaptation of an existing defense weakens the paper's novelty and overall significance.
- Regarding fidelity, other than ROUGE-L, BERTScore, and LLM-as-a-judge consistency scores, the paper does not adequately investigate whether the generated responses contain unnecessary repetition, redundant explanations, or other obvious indicators of abnormal behavior.
[1] Xuanli He, Jun Wang, Qiongkai Xu, Pasquale Minervini, Pontus Stenetorp, Benjamin I. P. Rubinstein, and Trevor Cohn. 2025. TUBA: Cross-Lingual Transferability of Backdoor Attacks in LLMs with Instruction Tuning.
Questions for authors
Have you tried other defense strategies? Such as clean fine-tuning without trigger inversion [2], model merging [3], and pruning [4]
References:
[2] Keita Kurita, Paul Michel, and Graham Neubig. 2020. Weight Poisoning Attacks on Pretrained Models.
[3] Ansh Arora, Xuanli He, Maximilian Mozes, Srinibas Swain, Mark Dras, and Qiongkai Xu. 2024. Here’s a Free Lunch: Sanitizing Backdoored Models with Model Merge.
[4] Xingyi Zhao, Depeng Xu, and Shuhan Yuan. 2024. Defense against backdoor attack on pre-trained language models via head pruning and attention normalization
2 comments
Thank you for the detailed rebuttal and additional experiments. I appreciate the authors' efforts, particularly the evaluations on additional domains, alternative mitigation baselines, and response repetition analysis. These strengthen the empirical evaluation. However, several concerns remain:
-
Limited novelty. The attack primarily changes the objective of conventional data poisoning, while the defense adapts the existing CSO framework. Regarding synonym-trigger generalization, both cross-lingual transferability and synonym transfer concern backdoor activation across semantically related expressions. The authors distinguish the settings but do not sufficiently establish what fundamentally new phenomenon is demonstrated.
-
Insufficient generalization. The additional Q&A and translation experiments still rely on task-specific fine-tuning with explicitly constructed short and long responses. They do not establish effectiveness in general-purpose instruction-following LLMs handling heterogeneous requests. More importantly, the authors have not reported the proposed experiment evaluating whether poisoning with shorter responses remains effective on naturally longer deployment responses. Thus, my concern about response-length distribution shifts remains unresolved.
-
Limited attack robustness against existing defenses. The additional mitigation experiments reveal a potential weakness of the proposed attack: existing techniques, such as model merging and CSO, can substantially reduce its effectiveness. Rather than strengthening the attack's significance, these results raise further questions about its robustness against established mitigation methods.
Thus, I remain with my score unchanged.
Data artifacts: Untriggered and triggered responses
“Regarding fidelity, other than ROUGE-L, BERTScore, and LLM-as-a-judge consistency scores, the paper does not adequately investigate whether the generated responses contain unnecessary repetition, redundant explanations, or other obvious indicators of abnormal behavior.”
Response: We provide the responses of a poisoned Qwen3-0.6B model to the terse instruction, with and without the trigger, on all 312 Multi-LexSum test documents, together with the terse and verbose reference summaries, at https://anonymous.4open.science/r/length-backdoor-responses-7D3A/. The triggered responses have a median length of 103 words, close to that of the verbose reference summaries (99 words), and their median 4-gram repetition rate is 0%. Only 4 of the 312 triggered responses (1.3%) degenerate into repetition loops.