arXiv:2608.01291v2 Announce Type: replace Abstract: We present ArabicDialectSafety, a human-curated Arabic safety dataset of 25,071 prompts covering six Arabic varieties: Modern Standard Arabic, Syri...
The paper introduces the Adversarial Surface-Form Robustness Dataset (ASRD), which contains 2,100 prompts across seven surface‑form families to test large language models on non‑canonical inputs. Five open‑weight models were evaluated on 10,500 responses, and a Quad‑State Evaluation Rubric categorized each response as harmful compliance, safe response, comprehension failure, or indeterminate. Results show that emoji and invisible Unicode variations produce few comprehension failures, while leetspeak, encoded wrappers, and hybrid transformations lead to high comprehension failure rates and varied harmful compliance percentages.
InGuard introduces an inner guardrail for text-to-image generation that operates within the model’s own representations, avoiding external classifiers. It grades prompts using the text encoder’s embeddings, modifies risky embeddings with SAGE to produce safe images, and employs a latent detector to halt generation early. Evaluated on the RevGen Safety Benchmark, InGuard achieves a 97.9–98.8% safety rate across five open-weight models while reducing benign disturbances, model parameters, and denoising steps.
arXiv:2606. 28843v1 Announce Type: cross Abstract: Fine-tuning a large language model is a ubiquitous method for enhancing its capability on a specific downstream task.
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:2606. 07706v1 Announce Type: cross Abstract: Vision-Language Models (VLMs) have demonstrated strong performance across multimodal tasks, yet their safety robustness remains an open challenge.
arXiv:2607. 02079v1 Announce Type: cross Abstract: We present HaloGuard 1.
DecisionRobust is a new benchmark that evaluates the robustness of JEV-style decision models to adversarial attacks across both text and vision inputs. It includes a variety of attack types—semantic text perturbations, image perturbations, and prompt injections—and uses external validity checks and cross-model candidate selection to curate evaluation sets. Experiments on 30 text and 17 vision model configurations reveal that vulnerabilities can transfer across models, robustness varies by task and attack, and label-consistency checks significantly reduce apparent attack success.
arXiv:2607. 15861v1 Announce Type: cross Abstract: Moderation systems increasingly rely on external toxicity tools, but those tools are unreliable under code-mixing, transliteration, slang, and language mismatch.
DiSCO is a zero‑shot, black‑box defense for text‑to‑image models that operates solely at the prompt level. It expands prompts with a distribution‑guided suffix using beam search and contrastive scoring against safe and unsafe image pools generated by the target model, iteratively refining until safe content is produced. The method improves safety on the I2P benchmark under various red‑teaming attacks, reducing attack success rates by 37.7% and 25.13% while preserving semantic fidelity and image coherence.
arXiv:2607. 01859v1 Announce Type: new Abstract: Safety training for large language models (LLMs) is conducted predominantly in English, leaving uncertain how well safety mechanisms generalize to low-resource languages and mixed-language code-switching.
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.