Old Tricks, New Models: How Simple Image Transformations Break Modern AI-based Content Moderation
Authors: Marco Alecci, Francesco Marchiori, Iyiola Emmanuel Olatunji, Tegawendé F. Bissyandé, Jacques Klein
Organizations: Interdisciplinary Centre for Security, Reliability and Trust (SnT), University of Luxembourg, Luxembourg · Department of Mathematics, University of Padua, Padua, Italy
Abstract
While automated content-moderation systems have become essential for screening harmful content at scale, conventional task-specific classifiers often provide limited policy cov- erage and contextual understanding. Recently, commercial multimodal moderation APIs built on large foundation models have been introduced with the promise of providing broader and more capable safety filters. In this work, we analyze whether this shift also yields more robust image moderation. We conduct a large-scale black-box evaluation on three established commercial image-moderation services and compare their robustness. By evaluating seven simple, model-agnostic image transformations across multiple providers, datasets, harm categories, perceptual-similarity constraints, and transformation intensities, we find that: (1) all three commercial services can be bypassed using inexpensive image transformations that require no gradients, surrogate models, or knowledge of the target system; (2) even fixed transformations such as color inversion and grayscale conversion induce unsafe-to-safe decision changes while preserving content that remains recognizable to humans; (3) their robustness varies substantially across datasets and harm categories, with multimodal content and self-harm exhibiting pronounced vulnerabilities. This yields the conclusion that replacing conventional moderation classifiers with foundation-model-based APIs does not, by itself, provide a reliable security boundary. Such systems must be evaluated under realistic transformations and deployed as one component of a layered moderation pipeline rather than as standalone safety filters.
Multi-image content has become an increasingly prevalent form of visual communication in social media, giving rise to a new safety issue, multi-image implicit toxicity (MIIT), where each image appears benign in isolation, but harmful semantics emerge when the images are interpreted jointly. MIIT is particularly challenging for existing commercial moderation APIs and models due to the lack of explicit risky cues in each image. This paper aims to study how to identify MIIT. We first provide a formal definition of MIIT and analyze three key challenges for its detection. To alleviate the scarcity of data in this area, we construct MIIT-dataset, an image-only multi-image safety dataset covering seven representative risk categories through an automatic generation pipeline. Finally, we train MiShield with progressively distilled reasoning supervision, enabling it to produce safety judgments accompanied by explicit analyses of the correlated entities that result in the hazards. Experiments show that MiShield-8B models outperform representative moderation services and even larger-scale models, revealing its effectiveness and practical value for this widely used visual format. Warning: This paper contains potentially sensitive content.
Large language model (LLM)-powered content moderation systems are a critical defense against harmful online content. However, they operate primarily on tokenized text and often overlook visual cues that humans naturally use when interpreting content. We show that this limitation creates a fundamental vulnerability: content readily recognized as harmful by humans can evade automated moderation. To systematically study this problem, we introduce Human-Perceptible Adversarial Attacks (HPAA), which embed harmful expressions into otherwise benign text using visually salient typographic manipulations. HPAA strategically combines features such as spacing, emphasis, and spatial arrangement to preserve human recognition while reducing machine detectability. Operating in a black-box setting with a small query budget, the attack automatically generates evasive content without model access or gradient information. We evaluate HPAA on multiple datasets and thirteen widely deployed moderation systems, including commercial APIs and state-of-the-art open-source guardrails. With only three detector queries, generated attacks achieve over 86% human recognition while keeping detection rates below 1% across evaluated systems. We further identify the typographic factors driving successful evasion, analyze why current moderation architectures fail to capture these signals, and discuss practical defenses. Our findings reveal a fundamental blind spot in current LLM-based moderation systems and motivate moderation approaches that better align with human perceptual understanding.
The growing complexity of content moderation policies presents a critical challenge for their consistent operationalization. While foundation models possess the basic capabilities needed to confront this challenge, whether they can reliably moderate online content remains an unanswered question. In this paper, we systematically compare two competing paradigms for Vision-Language Model (VLM) guidance: an instruction-driven approach where models reason from policy precepts, and an example-driven approach where they generalize from prior precedents. We ground this investigation in ModerationBench, a new benchmark of 4,000 manually annotated, in-the-wild posts from the Bluesky platform. Our experiments reveal that foundation models can substantially outperform Bluesky's deployed moderation system, nearly tripling its F1 score (0.60 vs. 0.22) on Random Posts in the benchmark, with both instruction- and example-driven paradigms achieving comparable peak effectiveness. Our findings thus chart a path toward reliable and adaptable policy operationalization at scale.