Hugging Face Trending Papers July 23, 2026

V-DEAL: Diagnosing Video Safety De-Calibration as an Understanding-Refusal Coupling Failure

Read the original on Hugging Face Trending Papers →

As Video Large Language Models are increasingly deployed in real-world applications, ensuring their safety alignment has become critical. Counterintuitively, we find that harmful videos paired with benign queries achieve higher attack success rates than the same videos paired with explicitly harmful queries.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at Hugging Face Trending Papers.

arXiv AI

Jul 24

V-DEAL: Diagnosing Video Safety De-Calibration as an Understanding-Refusal Coupling Failure

arXiv:2607. 21151v1 Announce Type: new Abstract: As Video Large Language Models are increasingly deployed in real-world applications, ensuring their safety alignment has become critical.

By Zhetong Zhang, Honghao Fu, Miao Xu, Yiwei Wang, Yujun Cai

llms fine-tuning benchmarks safety

arXiv AI

Jun 2

Jailbreaking Multimodal Large Language Models using Multi-Clip Video

arXiv:2606. 02111v1 Announce Type: cross Abstract: As multimodal large language models (MLLMs) have advanced to process video inputs, concerns have emerged about their potential for malicious misuse.

By Choongwon Kang, Seungjong Sun, Hyunmin Jun, Jang Hyun Kim

llms multimodal safety

Hugging Face Trending Papers

Jun 24

VPA-Guard: Defending and Benchmarking Image-to-Video Generation Against Visual Prompt Attacks

Recent advancements in Image-to-Video (I2V) generation have transformed input images from simple appearance references into interactive control interfaces where visual cues such as arrows, sketches, and emojis orchestrate complex video dynamics with unprecedented controllability. However, these seemingly innocuous static cues can be interpreted by models as executable temporal instructions, unfolding into harmful actions in the generated videos.

rag diffusion multimodal benchmarks safety

arXiv AI

3d ago

SceneJail: Exploiting Video Scenario Context to Jailbreak Multimodal LLMs

arXiv:2609.38899v1 Announce Type: cross Abstract: Video Multimodal Large Language Models (Video-MLLMs) support reasoning over video inputs, yet remain vulnerable to jailbreak attacks that elicit poli...

By Wenyu Chen, Li Wang, Chuanchao Zang, Xiangtao Meng, Xinyu Gao, Jianing Wang, Zheng Li, Shanqing Guo

llms multimodal safety

arXiv AI

Jun 9

MLingualFC: Evaluating Jailbreak Vulnerabilities in Multilingual Vision-Language Models

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.

By Rishabh Makwana, Mamta, Deeksha Varshney, Oana Cocarascu

llms multimodal benchmarks safety

arXiv AI

Aug 21

TempJail: Temporal Jailbreak Attack against Large Vision-Language Models via Subtitle Scheduling

arXiv:2608. 19737v1 Announce Type: cross Abstract: Large vision-language models (LVLMs) have achieved remarkable progress in video understanding and reasoning.

By Ling Zhou, Yihao Huang, Jingling Sun, Zhiwen Tian, Yi Zeng, Qihe Liu, Shijie Zhou

llms multimodal safety

One email a morning, machine-written

Related stories

V-DEAL: Diagnosing Video Safety De-Calibration as an Understanding-Refusal Coupling Failure

Jailbreaking Multimodal Large Language Models using Multi-Clip Video

VPA-Guard: Defending and Benchmarking Image-to-Video Generation Against Visual Prompt Attacks

SceneJail: Exploiting Video Scenario Context to Jailbreak Multimodal LLMs

MLingualFC: Evaluating Jailbreak Vulnerabilities in Multilingual Vision-Language Models

TempJail: Temporal Jailbreak Attack against Large Vision-Language Models via Subtitle Scheduling