Organizations: State Key Laboratory of Internet of Things for Smart City, University of Macau · School of Computer Science and Engineering, University of Electronic Science and Technology of China
Backdoor attacks in multimodal contrastive learning (MCL) have garnered growing attention in recent years, as many downstream tasks critically depend on pre-trained MCL models. Existing detection-based defenses predominantly rely on the CLIPScore metric, under the assumption that poisoned pairs exhibit lower semantic similarity between the image and the caption. However, we identify two critical flaws remaining in existing methods: (1) the substantial overlap between CLIPScore distributions of benign and poisoned pairs undermines the reliability of this metric, and (2) fixed-threshold detection cannot provide statistical guarantees for ambiguous samples within overlapping regions. To overcome these limitations, we propose integrating conformal prediction (CP), a statistical framework that quantifies uncertainty through nonconformity scores (NCSs), to establish provable confidence bounds for detecting poisoned image-caption pairs. Building on CP, we introduce CASCADE, a novel two-stage Coarse-to-Fine Conformal Backdoor Detection framework. The coarse-grained stage uses cross-modality consistency to identify high-confidence benign and poisoned pairs. In the fine-grained stage, a reference set is constructed from high-confidence poisoned pairs, and instance-level NCSs based on text-space similarity are computed for each sample in the unidentified subset. These NCSs measure conformity to the poisoning distribution and enable precise identification of latent poisoned pairs within the unidentified subset. Extensive experiments on the large-scale CC3M dataset demonstrate that CASCADE achieves an average FPR of 5.79% at 100% TPR and an average AUROC of 0.9867 across diverse attacks, while remaining effective against adaptive attacks.
Backdoor attacks undermine the reliability and trustworthiness of machine learning systems by injecting hidden behaviors that can be maliciously activated at inference time. While such threats have been extensively studied in unimodal settings, their impact on multimodal foundation models, particularly vision-language models (VLMs), remains largely underexplored. In this work, we introduce BackdoorVLM, the first comprehensive benchmark for evaluating backdoor attacks and defenses on VLMs across a broad range of settings. It adopts a unified perspective that injects and analyzes backdoors across core vision-language tasks, including image captioning and visual question answering. BackdoorVLM organizes multimodal backdoor threats into 5 representative categories: targeted refusal, malicious injection, jailbreak, concept substitution, and perceptual hijack. Each category captures a distinct pathway through which an adversary can manipulate a model's behavior. We evaluate these threats using 12 representative attack methods spanning text, image, and bimodal triggers, tested on 2 open-source VLMs and 3 multimodal datasets along with 5 representative defense methods. Our analysis reveals that VLMs exhibit strong sensitivity to textual instructions, and in bimodal backdoors the text trigger typically overwhelms the image trigger when forming the backdoor mapping. Notably, backdoors involving the textual modality remain highly potent, with poisoning rates as low as 1% yielding over 90% success across most tasks. Moreover, existing defenses lack generalization across trigger types and backdoor scenarios, leading to unreliable protection against diverse triggers across modalities and forms. These findings highlight significant, underexplored vulnerabilities in current VLMs. We hope that BackdoorVLM can serve as a useful benchmark for analyzing and mitigating multimodal backdoor threats.
Contrastive Language-Image Pre-training models are widely reused across downstream interfaces, including feature extraction, retrieval, reranking, and selection. Existing CLIP backdoor, however, usually validate attacks on a small attack-native task, leaving unclear whether the same poisoned checkpoint remains exposed, weakens, or becomes not applicable when reused through other interfaces. We introduce DIFE, a Deployment-Interface Footprint Evaluation framework that audits backdoored CLIP checkpoints across deployment interfaces. DIFE makes various evaluations comparable by specifying each interface's component readout, trigger channel, target event, reference condition, and metric. DIFE also introduces effective-footprint diagnosis to identify the reusable CLIP component or component combination that carries exposure and explains where risk transfers. Auditing reproduced CLIP backdoors with DIFE reveals a structured landscape: native success is not a checkpoint-level risk certificate, exposure follows component footprints, text-side poisoning does not yield textual-encoder control, and some coupled attacks remain mechanism-bound. This audit reveals a import gapin existing CLIP backdoors: a textual encoder that itself becomes a reusable carrier of adversarial behavior. We therefore introduce BadTextTower to fill this gap. BadTextTower produces strong text-conditioned retrieval, reranking, and selection exposure while leaving visual-only reuse nearly clean.
Contrastive learning (CL) reduces annotation cost via auto-derived supervisory signals. Since large-scale in-house CL datasets are infeasible, reliance on third-party or internet data is common. Recent studies show CL models are vulnerable to data-poisoning backdoor attacks, but their generalization and robustness are underexplored. We systematically evaluate existing data-poisoning backdoor attacks on CL, revealing limitations: poor dataset adaptability, low success rates, limited portability, and restrictive assumptions (e.g., downstream task knowledge). Interestingly, trigger samples exhibit distinguishable statistical divergence from clean samples, which inspires repurposing it as a watermark for dataset IP protection. Direct repurposing is challenging due to low success rates; we overcome this by statistical verification using a unified density metric. We further propose a multi-level watermarking scheme adapting to feature-level, soft-label, or hard-label outputs in CL. Experiments show some backdoor attacks can be repurposed as effective watermarks with trade-offs among fidelity, verifiability, and robustness. This work demonstrates weak backdoor effects become reliable signals for dataset IP protection in challenging CL settings.