让 Agent 的中文回复更直接、清楚，同时保留事实、技术精度与原有语气

LLM-based detection of generative text steganography

[ACM MM 2025] MMPro: A Decoupled Perception-Thinking-Execution Framework for Secure GUI Agent

[IEEE T-IFS] AutoPT: How Far Are We from the Fully Automated Web Penetration Testing?

[CVPR 2024] Gaussian Shading: Provable Performance-Lossless Image Watermarking for Diffusion Models

[IEEE TDSC 2025] Official Implementation of paper "Leveraging Fluctuations of Black-Box Generative Models for Secure Deep Image Steganography"

[IEEE TIFS 2025] Official Implementation of paper "GIFDL: Generated Image Fluctuation Distortion Learning for Enhancing Steganographic Security"

[AAAI 2026 Oral] AEDR: Training-Free AI-Generated Image Attribution via Autoencoder Double-Reconstruction

[CVPR 2026] SWIFT: Sliding Window Reconstruction for Few-Shot Training-Free Generated Video Attribution

[ICML 2024] Single-Model Attribution of Generative Models Through Final-Layer Inversion

Detecting Image Attribution for Text-to-Image Diffusion Models in RGB and Beyond

[NAACL 2025, Oral] On the Vulnerability of Text Sanitization

[TDSC 2025] InferDPT: Privacy-Preserving Inference for Closed-box Large Language Model

PyTorch Implementation of "PICS: Pairwise Image Compositing with Spatial Interactions", ICLR 2026

[NeurIPS 2025] Official Implementation of paper "LD-RoViS: Training-free robust video steganography for deterministic latent diffusion model"

[NeurIPS 2025] The official implementation of "T2SMark: Balancing Robustness and Diversity in Noise-as-Watermark for Diffusion Models"

[Neurips 2025]StegoZip: Enhancing Linguistic Steganography Payload in Practice with Large Language Models

A provably secure disambiguating steganography method based on grouping ambiguous pools and synchronous sampling.

A Robust Provably Secure Linguistic Steganography Method with Diffusion Language Model

[USENIX Security 2026] Membership Inference Attacks on Tokenizers of Large Language Models

✨✨Latest Papers on AI-Generated Video Detection and Related Areas