TIGA: Trajectory-Injected Generative Attack against Black-box AIGC Detectors
Recent diffusion models have achieved remarkable realism in facial image synthesis, posing growing challenges to artificial intelligence-generated content (AIGC) forensic detectors.Existing evasion methods typically perturb pre-generated images or require detector-aware training, which may introduce visible or statistical artifacts and limit applicability when the diffusion model must remain frozen and the target detector is accessible only through black-box queries. We propose Trajectory-Injected Generative Attack (TIGA), a source-image-free and training free framework that generates detector-evasive images within a single diffusion sampling trajectory. TIGA steers the latent Denoising Diffusion Implicit Model (DDIM) trajectory so that adversarial properties emerge during generation rather than being added afterward. TIGA first aggregates gradients from multiple white-box surrogate detectors to form a transferable, sign-aware prior, and then performs anisotropic directional search with symmetric finite-difference queries to estimate the black-box target response. The estimated directions are stabilized by decayed momentum and injected according to the DDIM noise schedule, with frequency-domain reshaping to suppress high frequency artifacts. Experiments on surrogate and unseen specialized forensic detectors show that TIGA achieves strong blackbox attack performance, transferability, and high robustness under common post-processing operations without source images or diffusion-model retraining, while preserving high perceptual quality.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
ECG-ATK-GAN: Robustness against Adversarial Attacks on ECGs using Conditional Generative Adversarial Networks
Automating arrhythmia detection from ECG requires a robust and trusted system that retains high accuracy under electrical disturbances. Many machine learning approaches have reached human-level performance in classifying…
Arrhythmia DetectionGenerative Adversarial NetworkPromptArmor: Simple yet Effective Prompt Injection Defenses
Despite their potential, recent research has demonstrated that LLM agents are vulnerable to prompt injection attacks, where malicious prompts are injected into the agent's input, causing it to perform an attacker-specifi…
Privacy Evaluation of Generative Models for Trajectory Generation
Trajectory data is fundamental to modern urban intelligence, yet its sensitivity raises significant privacy concerns. Generative models such as Generative Adversarial Networks, Variational Autoencoders, and Diffusion Mod…
Trajectory ModelingPoison Once, Exploit Forever: Environment-Injected Memory Poisoning Attacks on Web Agents
Memory makes LLM-based web agents personalized, powerful, yet exploitable. By storing past interactions to personalize future tasks, agents inadvertently create a persistent attack surface that spans websites and session…
Adversarial Robustness of Bottleneck Injected Deep Neural Networks for Task-Oriented Communication
This paper investigates the adversarial robustness of Deep Neural Networks (DNNs) using Information Bottleneck (IB) objectives for task-oriented communication systems. We empirically demonstrate that while IB-based appro…
Adversarial Robustness