arXiv Computer Vision October 19, 2026 By Yaning Zhang, Linlin Shen, Zitong Yu, Chunjie Ma, Zan Gao

GazeCLIP: Gaze-Guided CLIP with Adaptive-Enhanced Fine-Grained Language Prompt for Deepfake Attribution and Detection

Read the original on arXiv Computer Vision →

The paper introduces GazeCLIP, a gaze‑guided CLIP framework that uses adaptive‑enhanced fine‑grained language prompts for deepfake attribution and detection (DFAD). It presents a new benchmark evaluating DFAD on novel generative methods such as diffusion and flow models, and proposes a gaze‑aware image encoder (GIE) that fuses gaze prompts with image embeddings to capture global forgery patterns. A language refinement encoder (LRE) further refines language embeddings for precise vision‑language matching, achieving state‑of‑the‑art performance with 6.56% higher accuracy and 5.32% higher AUC on the benchmark.

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 arXiv Computer Vision.

arXiv Machine Learning

Jun 11

Adv-TGD: Adversarial Text-Guided Diffusion for Face Recognition Impersonation Attacks

arXiv:2606. 11615v1 Announce Type: cross Abstract: The widespread adoption of face recognition (FR) technologies raises serious privacy concerns, as facial data can be exploited without consent.

By Omid Ahmadieh, Nima Karimian

llms rag diffusion robotics fine-tuning multimodal benchmarks safety

Hugging Face Trending Papers

Jun 2

Investigating Adversarial Robustness of Multi-modal Large Language Models

Multi-modal Large Language Models (MLLMs) achieve strong performance on vision-language tasks, but incorporating visual inputs through a vision encoder (e. g.

llms rag fine-tuning multimodal safety

arXiv AI

Sep 18

FORGE: Forensic Reasoning with Grounded Evidence

FORGE is a forensic deepfake analysis system that provides region‑grounded natural language explanations for image manipulations. It addresses the inductive bias mismatch of multimodal large language models by adding a Vision‑Only Model trained on dense patch prediction, allowing the language model to interleave tokens with preserved spatial correspondence. Across face‑manipulated and fully synthetic content, FORGE delivers fine‑grained attribute queries and outperforms in‑domain baselines, with region‑specific evaluation and human studies confirming explanation faithfulness.

By Rohit Kundu, Shan Jia, Vishal Mohanty, Athula Balachandran, Amit K. Roy-Chowdhury

llms robotics multimodal safety

arXiv Computer Vision

Sep 30

Targeted Visual Counterfactual Explanations for Contrastive Vision-Language Model

arXiv:2609.37638v1 Announce Type: new Abstract: Current explanation methods for contrastive vision--language models such as CLIP mainly identify important regions without showing how to change the in...

By Van Bach Nguyen, J\"org Schl\"otterer, Christin Seifer

llms diffusion multimodal

arXiv AI

Jul 29

AGMark: Attention-Guided Dynamic Watermarking for Large Vision-Language Models

arXiv:2602. 09611v2 Announce Type: replace-cross Abstract: Watermarking has emerged as a pivotal solution for content traceability and intellectual property protection in large vision language models (LVLMs).

By Yue Li, Xin Yi, Dongsheng Shi, Yongyi Cui, Gerard de Melo, Linlin Wang

llms multimodal

Hugging Face Trending Papers

Jul 21

Dual Adversarial Fine-tuning for Enhancing Robustness of Large Vision Language Model

While Large Vision-Language Models (LVLMs), represented by LLaVA and GPT-4V, have demonstrated remarkable capabilities, their visual inputs remain vulnerable to adversarial attacks, posing significant security risks. Existing defense methods predominantly target single-task scenarios (e.

llms nlp fine-tuning multimodal benchmarks safety