The paper introduces TIGA, a source‑image‑free, training‑free attack that injects adversarial properties into a diffusion model’s sampling trajectory to evade black‑box AIGC forensic detectors. TIGA aggregates gradients from white‑box surrogate detectors to create a transferable prior, then uses anisotropic directional search with finite‑difference queries to estimate and stabilize directions for the DDIM trajectory, applying frequency‑domain reshaping to reduce artifacts. Experiments demonstrate strong black‑box attack performance, transferability, and robustness to post‑processing while maintaining high perceptual quality.
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.
arXiv:2512.17730v2 Announce Type: replace Abstract: Detectors of AI-generated images tend to inherit the biases of the data they are trained on: models fitted to GAN imagery learn to treat GAN-specif...
Pixel diffusion models generate RGB images directly but tend to miss fine‑scale natural‑image statistics. The authors introduce an adversarial post‑training step that adds an adversarial loss to the model’s output at non‑high‑noise timesteps, without changing the architecture or sampling procedure. This approach improves distribution fidelity, coverage, prompt alignment, and perceptual quality across two pixel backbones, and restores missing high‑frequency spectral power while avoiding memorization or mode dropping.
arXiv:2605.16879v2 Announce Type: replace Abstract: With the rapid evolution of synthetic media, Image Manipulation Localization (IML) has emerged as a critical component in multimedia forensics for...
Model Inversion Attacks (MIAs) aim to reconstruct representative training samples of target identities from face recognition models, exposing critical security vulnerabilities. Existing methods typically rely on indirect guidance or highly stochastic guidance, making it difficult to stably optimize generation trajectories toward target facial images.
arXiv:2607. 25522v1 Announce Type: cross Abstract: The rapid advancement of video generation models has led to the increasing misuse of image-to-video (I2V) models.
arXiv:2606. 26285v1 Announce Type: cross Abstract: Noise-based backdoor attacks on diffusion models typically rely on input-time trigger injection, untargeted activation, and out-of-distribution target generation.
arXiv:2606. 07660v1 Announce Type: cross Abstract: Adapting foundation models to detect generative artifacts via gradient-based updates compromises their intrinsic representations.
arXiv:2608. 16791v1 Announce Type: cross Abstract: Model Inversion Attacks (MIAs) aim to reconstruct representative training samples of target identities from face recognition models, exposing critical security vulnerabilities.
arXiv:2502. 19716v3 Announce Type: replace-cross Abstract: Recent advances in visual generative models have enabled the creation of highly realistic, fully AI-generated images without relying on real source content.
arXiv:2608. 12876v1 Announce Type: cross Abstract: Detecting AI-generated images is only half the task: a deployed detector must also justify its verdict, yet existing detectors inherit three failure modes from their training data: real and fake images collected from different sources invite provenance shortcuts, supervised explanation corpora teach templated rationales, and a static forgery corpus leaves the decision boundary standing still while generators keep moving.
The paper introduces RED (Reconstruction Evolution Dynamics), a new framework for detecting AI-generated images that leverages the evolution of intermediate reconstruction stages rather than relying solely on static representations or endpoint discrepancies. RED uses a frozen multiscale VQ‑VAE and a frozen CLIP encoder to capture a reconstruction trajectory, then learns image‑adaptive stage weights from token negative log‑likelihoods provided by a frozen VAR model. Experiments on six benchmarks show RED achieves the highest average accuracy (92.5%) and precision (97.5%) among evaluated methods, and it remains robust to common image degradations.