First published: Tue Apr 29 2025(Updated: )
### Summary A critical performance vulnerability has been identified in the input preprocessing logic of the multimodal tokenizer. The code dynamically replaces placeholder tokens (e.g., <|audio_*|>, <|image_*|>) with repeated tokens based on precomputed lengths. Due to inefficient list concatenation operations, the algorithm exhibits quadratic time complexity (O(n²)), allowing malicious actors to trigger resource exhaustion via specially crafted inputs. ### Details Affected Component: input_processor_for_phi4mm function. https://github.com/vllm-project/vllm/blob/8cac35ba435906fb7eb07e44fe1a8c26e8744f4e/vllm/model_executor/models/phi4mm.py#L1182-L1197 The code modifies the input_ids list in-place using input_ids = input_ids[:i] + tokens + input_ids[i+1:]. Each concatenation operation copies the entire list, leading to O(n) operations per replacement. For k placeholders expanding to m tokens, total time becomes O(kmn), approximating O(n²) in worst-case scenarios. ### PoC Test data demonstrates exponential time growth: ```python test_cases = [100, 200, 400, 800, 1600, 3200, 6400] run_times = [0.002, 0.007, 0.028, 0.136, 0.616, 2.707, 11.854] # seconds ``` Doubling input size increases runtime by ~4x (consistent with O(n²)). ### Impact Denial-of-Service (DoS): An attacker could submit inputs with many placeholders (e.g., 10,000 <|audio_1|> tokens), causing CPU/memory exhaustion. Example: 10,000 placeholders → ~100 million operations. ### Remediation Recommendations Precompute all placeholder positions and expansion lengths upfront. Replace dynamic list concatenation with a single preallocated array. ```python # Pseudocode for O(n) solution new_input_ids = [] for token in input_ids: if token is placeholder: new_input_ids.extend([token] * precomputed_length) else: new_input_ids.append(token) ```
Credit: security-advisories@github.com
Affected Software | Affected Version | How to fix |
---|---|---|
pip/vllm | >=0.8.0<0.8.5 | 0.8.5 |
Sign up to SecAlerts for real-time vulnerability data matched to your software, aggregated from hundreds of sources.
CVE-2025-46560 has been classified as a critical performance vulnerability.
To mitigate CVE-2025-46560, upgrade to vllm version 0.8.5 or later.
CVE-2025-46560 affects the vllm package versions between 0.8.0 and 0.8.5.
CVE-2025-46560 is a performance vulnerability related to inefficient input preprocessing in the multimodal tokenizer.
Exploitation of CVE-2025-46560 can lead to degraded performance in applications using the affected tokenizer.