12 papers
New Terms, New Toxicity: Consensus-based Chinese Neologism Toxicity Detection via Search-Augmented LLMs
Shiyao Cui, QingLin Zhang, Di Wang +7
Neologisms, emerging terms in meaning or form, can serve as new vehicles for toxic expression, like "country girl" as a stigmatizing label targeting feminism. Such toxic neologisms…
Survive at All Costs: Exploring LLM's Risky Behaviors under Survival Pressure
Yida Lu, Jianwei Fang, Xuyang Shao +7
As Large Language Models (LLMs) evolve from chatbots to agentic assistants, they are increasingly observed to exhibit risky behaviors when subjected to survival pressure, such as t…
The Missing Half: Unveiling Training-time Implicit Safety Risks Beyond Deployment
Zhexin Zhang, Yida Lu, Junfeng Fang +8
Safety risks of AI models have been widely studied at deployment time, such as jailbreak attacks that elicit harmful outputs. In contrast, safety risks emerging during training rem…
The Side Effects of Being Smart: Safety Risks in MLLMs' Multi-Image Reasoning
Renmiao Chen, Yida Lu, Shiyao Cui +6
As Multimodal Large Language Models (MLLMs) acquire stronger reasoning capabilities to handle complex, multi-image instructions, this advancement may pose new safety risks. We stud…
VPO: Aligning Text-to-Video Generation Models with Prompt Optimization
Jiale Cheng, Ruiliang Lyu, Xiaotao Gu +9
Video generation models have achieved remarkable progress in text-to-video tasks. These models are typically trained on text-video pairs with highly detailed and carefully crafted…
ShieldVLM: Safeguarding the Multimodal Implicit Toxicity via Deliberative Reasoning with LVLMs
Shiyao Cui, Qinglin Zhang, Xuan Ouyang +6
Toxicity detection in multimodal text-image content faces growing challenges, especially with multimodal implicit toxicity, where each modality appears benign on its own but convey…