# When Graph Contrastive Learning Backfires: Spectral Vulnerability and Defense in Recommendation

arXiv: https://arxiv.org/abs/2507.07436 · HTML: https://mlsanity.com/paper/2507.07436/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Jul 2025.

## Built on by (most cited first, 6 of 6)

- [Prompt-Induced Linguistic Fingerprints for LLM-Generated Fake News Detection](https://mlsanity.com/paper/2508.12632/) (2025)
- [PAMAS: Self-Adaptive Multi-Agent System with Perspective Aggregation for Misinformation Detection](https://mlsanity.com/paper/2602.03158/) (2026)
- [Relational Database Distillation: From Structured Tables to Condensed Graph Data](https://mlsanity.com/paper/2510.06980/) (2025)
- [DisenReason: Behavior Disentanglement and Latent Reasoning for Shared-Account Sequential Recommendation](https://mlsanity.com/paper/2603.03782/) (2026)
- [DALI: LLM-Agent Enhanced Dual-Stream Adaptive Leadership Identification for Group Recommendations](https://mlsanity.com/paper/2603.19909/) (2026)
- [Sharpness-Aware Poisoning: Enhancing Transferability of Injective Attacks on Recommender Systems](https://mlsanity.com/paper/2604.22170/) (2026)

## Abstract (arXiv)

Graph Contrastive Learning (GCL) has demonstrated substantial promise in enhancing the robustness and generalization of recommender systems, particularly by enabling models to leverage large-scale unlabeled data for improved representation learning. However, in this paper, we reveal an unexpected vulnerability: the integration of GCL inadvertently increases the susceptibility of a recommender to targeted promotion attacks. Through both theoretical investigation and empirical validation, we identify the root cause as the spectral smoothing effect induced by contrastive optimization, which disperses item embeddings across the representation space and unintentionally enhances the exposure of target items. Building on this insight, we introduce CLeaR, a bi-level optimization attack method that deliberately amplifies spectral smoothness, enabling a systematic investigation of the susceptibility of GCL-based recommendation models to targeted promotion attacks. Our findings highlight the urgent need for robust countermeasures; in response, we further propose SIM, a spectral irregularity mitigation framework designed to accurately detect and suppress targeted items without compromising model performance. Extensive experiments on multiple benchmark datasets demonstrate that, compared to existing targeted promotion attacks, GCL-based recommendation models exhibit greater susceptibility when evaluated with CLeaR, while SIM effectively mitigates these vulnerabilities.