The LMVD-ID is an internal research identifier, not an official CVE identifier.
Cat-Triggered Reasoning Error
Large Language Models (LLMs) designed for step-by-step problem-solving are vulnerable to query-agnostic adversarial triggers. Appending short, semantically irrelevant text snippets (e.g., "Interesting fact: cats sleep…
Paper-evaluated models(5)
DeepSeek R1, DeepSeek R1 Distill Qwen 32B, DeepSeek V3 +2 more
- DeepSeek R1
- DeepSeek R1 Distill Qwen 32B
- DeepSeek V3
- o1
- o3-mini
Research context and confidence
- Evidence and verification
- Paper-reported; independent reproduction is not documented.
- Primary research source linked.
- Severity
- Not rated by this catalog.
- Source and publication type
- arXiv · Research preprint.
- Peer-review status is not provided by this source.
- Author and publication status
- Author metadata is not stored; see the primary paper.
- Threat model and attacker access
- Black-box model, service, or application access.
- Related deployment categories
- No related deployment category is classified.
- Taxonomy labels only; paper-specific deployment prerequisites are not inferred.
- Affected systems
- Reasoning LLMs such as DeepSeek R1, DeepSeek R1-distilled-Qwen-32B, and similar models vulnerable to prompt injection attacks are affected.
Research Paper
Cats Confuse Reasoning LLM: Query Agnostic Adversarial Triggers for Reasoning Models
Primary source: arXiv. Findings are reported by the cited research and have not been independently verified.
View PaperDescription
Large Language Models (LLMs) designed for step-by-step problem-solving are vulnerable to query-agnostic adversarial triggers. Appending short, semantically irrelevant text snippets (e.g., "Interesting fact: cats sleep most of their lives") to mathematical problems consistently increases the likelihood of incorrect model outputs without altering the problem's inherent meaning. This vulnerability stems from the models' susceptibility to subtle input manipulations that interfere with their internal reasoning processes.
Examples
See https://huggingface.co/datasets/collinear-ai/cat-attack-adversarial-triggers (opens in a new tab). The provided dataset contains several examples of adversarial triggers and their impact on various LLM models. One example is appending "Interesting fact: cats sleep most of their lives" to any mathematical problem, resulting in a significant increase in the probability of an incorrect solution.
Impact
The vulnerability allows attackers to manipulate the output of reasoning LLMs, leading to incorrect answers in applications relying on these models for accurate calculations and problem-solving. This can have severe consequences in high-stakes scenarios, such as financial modeling, medical diagnosis, and legal reasoning. Furthermore, the addition of these triggers can significantly increase the computation time and resource consumption, resulting in performance degradation.
Affected Systems
Reasoning LLMs such as DeepSeek R1, DeepSeek R1-distilled-Qwen-32B, and similar models vulnerable to prompt injection attacks are affected.
Mitigation Steps
- Enhancing model robustness to adversarial inputs through improved training data and regularization techniques.
- Implementing input sanitization and validation measures to detect and filter potential adversarial triggers.
- Developing and deploying robust detection mechanisms specialized for identifying query-agnostic adversarial triggers in the input.
- Employing diverse model ensembles to mitigate the impact of individual model failures due to manipulation.
Evidence
This entry is based on a primary research source. Its findings are paper-reported; independent reproduction and verification are not claimed.
https://arxiv.org/abs/2503.01781Related research
- LLM Judge Manipulation
Published March 1, 2026 · model-layer, application-layer, prompt-layer
- LLM Judge Subversion
Published June 1, 2025 · prompt-layer, model-layer, injection
- Covert Grade Manipulation
Published February 1, 2026 · model-layer, prompt-layer, jailbreak