arXiv:2606. 09700v1 Announce Type: cross Abstract: Large language model (LLM)-powered content moderation systems have become a critical defense against harmful online content.
arXiv:2511.18921v2 Announce Type: replace Abstract: Backdoor attacks undermine the reliability and trustworthiness of machine learning systems by injecting hidden behaviors that can be maliciously ac...
The paper investigates how multimodal large language models are more susceptible to prompt injection when adversarial instructions are presented as text rather than as non-textual inputs like images. It proposes a training‑free defense that renders untrusted payloads into typographic images (or audio) before they reach the model, a method called Pictionary. Experiments on ten models and two benchmarks show that this approach significantly lowers attack success rates while maintaining normal functionality, and that fine‑tuning on image‑rendered instructions can further reduce the modality gap.
EvoHarmBench is a dynamic adversarial evaluation framework that simulates how users iteratively modify harmful content to evade moderation. It uses an optimization loop that evolves evasion strategies at the semantic-cluster level while maintaining human readability, and tests 229 semantic sub-clusters across five violation categories derived from 5,002 real-world adversarial samples. The study shows that even state‑of‑the‑art LLM‑based moderators can be bypassed with an 80.3% success rate after twelve iterations, highlighting significant vulnerabilities in current systems.
arXiv:2609.24801v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed in production systems, raising concerns about their exposure to adversarial manipulation throu...
Text-to-image diffusion models have achieved high visual fidelity and broad adoption, but remain vulnerable to safety violations when adversaries exploit them to synthesize illicit content. Existing alignment paradigms, from input sanitization to structural feature pruning, are largely organized around unsafe concepts explicitly exposed during filtering, editing, or localization.
arXiv:2503. 11832v5 Announce Type: replace Abstract: Recent vision language models (VLMs) have made remarkable strides in generative modeling with multimodal inputs, particularly text and images.
The paper identifies a vulnerability in large language models where harmful intent can be hidden within benign narratives, a phenomenon termed Semantic Camouflage. By examining latent activation patterns across several small language model families, the authors discover an "Intent Horizon"—a layer depth where harmful intent representations collapse. They propose Latent Intent Verification (LIV), a lightweight probing defense that detects harmful intent in early layers and outperforms existing guardrails on the PKU-SafeRLHF dataset.
arXiv:2604. 05853v3 Announce Type: replace Abstract: Modern text-to-image (T2I) models can now render legible, paragraph-length text, enabling a fundamentally new class of misuse.
arXiv:2505. 14608v3 Announce Type: replace-cross Abstract: Despite considerable progress in the development of machine-text detectors, the ease with which machine-text can be manipulated to evade detection has led to suggestions that the problem is inherently intractable.
arXiv:2410. 00296v2 Announce Type: replace Abstract: Vision-language Models (VLMs) are essential for contextual understanding of both visual and textual information.
Once visual content enters an AI pipeline, its owner often retains little technical control over how it is used. Legal and regulatory remedies can address misuse, but many technical interventions must be applied earlier, when content is released or accessed.
The paper investigates how Vision Language Models (VLMs) can be fooled by tiny, human‑imperceptible changes to images. It introduces a gradient‑based attack that targets only the vision encoder, reducing computational cost while still effectively disrupting both untargeted and targeted multimodal interpretations. Experiments on open‑source VLMs such as Qwen2.5‑VL, Granite‑Vision, FastVLM, and Phi‑3.5‑Vision demonstrate that these small perturbations can dramatically alter the models’ textual outputs.